As 2022 inches closer to the finish line, use cases for customer analytics and digital intelligence continue to evolve with a bottomless hunger for variety and volume of data to supercharge data science. Check in with any of the analytical magicians within your brand, and observe their struggle to acquire the relevant input data (and enough of it) to train their modeling recipes.   Sounds strange, right? The frequently used term of yester-year known as "BIG data" used to roll off the tongue as often as we hear the term "AI" today. The challenge isn't that there is enough information in general. But the intention of any analyst is to identify meaningful data signals to address business objectives. What's the point of having access to oceans of big data if it's just noise? Garbage in, garbage out. For example, I would like to build a classification model using supervised learning to improve our understanding of behaviors and drivers of conversion behavior for my B2C (business-to-consumer) brand.   - 99.5% of the customer journeys resulted in non-conversion for the past 90 days. - 0.5% resulted in a conversion.   If my analysis does a great job of accurately predicting non-conversions (high true negative rate), but does a terrible job of classifying conversions (low true positive rate), what marketing leader is going to get excited about that? Excluding special exceptions, not many. The problem here amplifies a well known problem in modeling related to a rare-event of interest.    Taking it one step further, as deep learning increases in practical application of business use cases, many observe the space as a foundational component of modern AI algorithms. But we also know to effectively train models using these algorithms, one needs a tremendous amount of data. And while it seems like we’re practically swimming in data day in and day out, we don’t necessarily always have enough of the RIGHT data for every process or behavior we’re trying to model. In other words, it's NOT the lack of choice of machine learning algorithms, but the scarcity of high-quality data.     Enter synthetic data for analytics, machine learning and AI which replicates, mirrors, or extracts look-alike information that allow analysts to model use cases that would otherwise be impractical. A few examples of challenges include:   - Data quality concerns - Privacy - Lack of relevant data   Image 1: Synthetic data generation use cases   But I work in the martech industry, how does this apply to me?    Real data is expensive to collect and properly annotate, especially when it is in large scale. This is both a monetary and time drain for high-utility team members who support customer journey management processes. Real data can also be messy, requiring time to clean and/or extract useful features. It can be imbalanced, which makes it harder to train good models in support of journey-based analytics. It can be sensitive to share or store due to privacy concerns.     Now, marketers frequently run campaigns, tasks and activities. They target audience segments. The desire is to deliver personalization that is helpful, relevant and value enhancing within tailored customer experiences across channels. Two examples of analytically-driven marketing to consider:   Propensity scores. They are intended to identify high-likelihood audiences who will convert on your macro- and micro-conversion goals. However, imbalanced data that is used to train classification models will produce higher margins of error, or less valuable propensity scores that lead to irrelevant personalization and lower conversion rates. Look-alike audience insights. You know you love it when an analyst describes to you the behaviors, demographics, and transactional patterns of high-value customers. The actionable outcome is to hunt for look-alikes within acquisition & upsell/cross-sell marketing. Imbalanced data is like a viral infection, and reduces the opportunistic potential of the insight-driven strategies being leveraged to influence the usage of marketing budgets.   Image 2: Customer journey management   Moving on, using real data about customers for training models can introduce risks in regard to adherence of regulatory requirements, as well as amplify existing biases that lead to negative CX outcomes for brands. While synthetic data alone is not a one-stop solution for data biases, it does enable the opportunity for identification and mitigation. Even brands that consider themselves data-rich should revisit if and how leveraging synthetic data might benefit their analytical use cases.   A trending example specific to martech centers on data sharing, clean rooms and co-ops. If a brand cannot keep their promise to customers to protect data, it can compromise their integrity. As a brand that puts your customer first, are you making every effort to do the right thing? Companies often express how seriously they take their customers’ privacy and security but then either can’t or won’t deliver. Regulators have obligated brands to demonstrate their accountability for handling personal data. However, when data gets shared and processed across complex ecosystems of partners, it’s problematic to assign clear ownership and accountability.   Across every corner of the martech industry, brands are focused on personalized and dynamic experiences in the customer moments that matter as a part of their digital experience aspirations. From offering increased automation and anticipation of customer needs, brands must collect the necessary Zero and 1st party customer data to fuel the insights that enable these experiences. Profitable growth and customer loyalty depend on it.   Every data-sharing use case has unique risks and requirements. Considerations about data types (personal or sensitive), the parties involved and the extension of the data-sharing ecosystem, as well as the purposes of the sharing will force brands to acutely identify their preferred method of approach. There is demand to deliver increasingly intelligent, engaging, and profitable applications/products, but this requires balancing against stronger pressure from regulators and the public to protect personal data/privacy. Synthetic data presents a viable solution by allowing brands to use their knowledge of existing customers to create look-alike data that mirrors the original data but preserves no identifiable connection to the individual customers.   Image 3 - Real vs. synthetic data correlation plot comparisons   Synthetic data can be artificially manufactured by special-purpose machine learning models in a way that captures the data distributions and patterns, while also helping to maintain privacy without exposing real information.  For example, a Generative Adversarial Network algorithm, or GAN, can learn the patterns and relationships in existing data in order to generate new observations that are indistinguishable from real data. You’ve probably seen this used for what are known as deep fakes (creating very realistic images of people that don’t even exist). But we can also use this same technology for tabular data, which is most common for training predictive models with machine learning algorithms.  The following demo will showcase the use of tabularGAN to generate synthetic data.       The demo showcased how powerful SAS is for data scientists and analysts (high/low/no-code) to methodically work through a process for generating synthetic data.  So if you are early on in data preparation and recognize you need more data or need to balance your data, or if you are in model development and realize you need more data either to train your models or to validate them, you can simply use SAS to kick off training a new GAN or using one that has already been trained for your data. Refer here for the synthetic data generation steps we used in this process.   SAS is well positioned to deliver a comprehensive experience to not only generate synthetic data programmatically, but also expand our reach into the no/low-code user base.   Image 4: Technology User Personas   The use cases for synthetic data are expanding every day, across the entire martech industry. We look forward to what the future brings in our development process – as we enable technology users to access all of the most recent SAS analytical developments. Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing here.       ... View more

As the proportion of online to offline customer interactions with a brand continues to elevate, both digital experiences and the 1st/Zero-party data that analytic solutions collect about them will mature in ways that will challenge and benefit insight -led companies. Over the years, we have observed the web/digital analytic ecosystem of software solutions and targeted users bury themselves in templated measurement reports primarily descriptive in nature. As digital data related to your customers continues to incrementally increase in importance, enterprise use cases for sharing insights broadly within their walls frequently attempt to absorb digital data signals into their business intelligence (BI) applications. However, many brands seem to be hitting an adoption ceiling.   Image 1: Measurement and reporting   At SAS, our perspective on this trend is the lack of customization (or personalization) that derails a digital measurement solution's attempt to be easy-to-use. Augmented data visualization and discovery is appealing because it does not subscribe to a one-size-fits-all user experience. To fully exploit the potential of analytic measurement, interactive visualization and distributed reporting, numerous dimensions should be considered:   Insights - Who will explore, identify & produce? How will they be explained? Most importantly, don't overlook how they will be consumed. Every brand will have a unique recipe of audience members who will receive insights, and their personal levels of data/analytical literacy matters.  Analysis - Web/digital analytic standalone solutions tend to skew more towards canned/guided delivery of insight. There's nothing wrong with that if you find this beneficial. But when brands link digital and non-digital data sources together, the flexibility to explore, share recipes of  approach & using technology that augments/accelerates the analysis workflow in arriving to unbiased, impactful insight conclusions is critical.   The commoditization of many core visualization capabilities is well underway, whether we like or not. But the game is far from over. SAS recognizes the critical importance of serving multiple enterprise personas through augmentation (embedded AI and machine learning to assist in report authoring and consumption.) This spectrum ranges from business users who want out-of-the-box benefits to savvy analysts who want to build assets from scratch. It is extremely challenging for any brand or supporting vendor to predict if a do-it-yourself (DIY) approach vs. a do-it-for-me (DIFM) approach will be more effective. SAS constantly observes, accepts and uses this challenge to inspire our software’s design principles to enable capabilities to reflect the balancing needs between marketers, analysts and data scientists within an organization.   Image 2: Technology user personas   Furthermore, what can AI do to keep improving insight-driven practices? It's natural within brands to see different flavors of analysts and martech team members express a desire to go beyond reporting, querying, data visualizations, and descriptive/diagnostic analytics. Augmentation introduces emerging capabilities worth noting:   Enabling users in no/low-code environments to identify key drivers or influencers on a metric, find anomalies, or project a forecast/trend supported with natural language generation (NLG) to ensure accurate interpretation of insights. What about data scientists and data engineers? It should not be overlooked that SAS Viya allows them to author and train new ML models in the same platform where models are going to be deployed, but it also eliminates the need to integrate multiple platforms, improving model transparency/governance, and reducing the likelihood of errors that may result from platform-to-platform data and metadata handoffs. After all, when a modeling project reaches completion, it is common to author and distribute reports that summarize the value models deliver to audiences with lower thresholds of analytical literacy.   Let's pivot and focus on how SAS supports digital customer analytic measurement and reporting. SAS Customer Intelligence 360 offers a single JavaScript tag to collect website 1st/Zero-party interaction and element level data, pixel tracking, mobile SDKs, server-to-server APIs, and tracking for native/hybrid apps. Once any of these data streams are absorbed, the SAS Customer Intelligence 360 unified data model (UDM) contextualizes this information into OOTB/customizable structured tables for analysis enabling do-it-for-me (DIFM) software user features & do-it-yourself (DIY) analyst acceleration.   The subject areas include session/event-based data for visits, media, pages, products, forms, search, goals, conversions, customers, web/mobile/email/direct marketing and contact/response. SAS provides over 100 prebuilt & customizable reports (including templates, metrics & KPIs) for campaigns, journeys, content, events, ecommerce and more. Users can create recipes & share using native SAS visualization or through integration w/ MS Power BI & open-source (Python, D3) to take advantage of customizable features for color, KPIs, sizing, responsive design, cross-device/streaming analytics, user annotations/alerting, extensibility to iOS/Android mobile apps & SDKs for custom/3rd party app/websites.    But enough chatter...let's get to the technology demos and bring this to life.   Technology demo: Augmented dashboards, reporting & measurement   To begin, we will briefly introduce standard OOTB reports to users of SAS Customer Intelligence 360. We will then transition to how 1st/Zero-party data captured & contextualized by SAS Customer Intelligence 360 can be made available to SAS Visual Analytics on SAS Viya. This will significantly expand the amount of customization that can be applied to dashboards and reports, as well as diversify the data sources that can be represented in these measurement assets. We will drill into the augmentation features that provide value propositions such as natural language generated insights, explanations, outlier detection, correlated measures, auto-segmentation & DIFM propensity-scoring. We will wrap up this demonstration in how these measurement reporting assets can be shared.     We look forward to what the future brings in our development process – as we enable marketing technology users to access all of the most recent SAS analytical developments. Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing  here .   ... View more

As we enter Q4 of 2022, SAS continues to address and innovate around the business challenge of managing customer journeys. As many of us know, a typical use case will involve multiple customer interactions with a brand's digital presence spanning over numerous sessions and touchpoints. Behind customer journeys, opportunities exist to take advantage of different types of data that can be collected, contextualized & analyzed to derive actionable insight. These learnings frequently motivate brands to launch experimental testing, behavioral targeting, personalization or recommendation systems to optimize the experience. SAS recognizes that optimization within customer journeys does not end, and iterates in sequential continuance requiring brands to explore new analytical approaches to support CX that can self-learn, improve and deliver results.   Image 1: Managing Customer Journeys   Although this article will be skewed to transparent technology demonstrations, I should disclose that SAS Customer Intelligence 360 & SAS Viya provide comprehensive DataOps, ModelOps & CX orchestration in an integrated platform. There are no constraints for data access (cloud/hybrid/on-premises), dashboarding, visualization, segmentation (rules-/algorithmic-based) & self-service usability w/ varying degrees of automation infused by design for do-it-for-me (DIFM) & do-it-yourself (DIY) software users.   Image 2: Technology User Personas   Let's provide a demo preview:   Chapter 1 will showcase a customer journey that is triggered from real-time user behavior. SAS Customer Intelligence 360 will detect this user event by contextualizing streaming semi-structured clickstream and igniting a customer journey activity map. Next in Chapter 2, as the customer browses a retail brand's website, various examples of behavioral targeting using a recently released OOTB system connector between SAS Customer Intelligence 360 and SAS Intelligent Decisioning on Viya simplifies the deployment of customizable business rules & DIFM/DIY machine learning that will ultimately result the user to convert onsite. Finally, Chapter 3 will pivot from acquisition to upsell/cross-sell within the journey nurtured by additional touchpoint interactions across an instrumented mobile app and email with analytically-driven personalization offers. But what drove those offers? Propensity scores, clusters or CDP black box magic? Actually, we will use an application of reinforcement learning and exemplify how SAS optimizes offers orchestrated through SAS Customer Intelligence 360. Although experiment designs like A/B/n & MVT (Multivariate) can be used, we will demonstrate the use of RL Contextual Bandits natively available in SAS Visual Data Mining & Machine Learning on Viya to support aspects of self-learning that do not exist in the aforementioned testing methods.    Image 3: Decisioning Within Customer Journey Interactions   Chapter 1: Customer Journey Activation   In SAS Customer Intelligence 360, events enable users to enhance their ability to understand, target, and interact with customers in a meaningful way. Events are used to track user behavior and to provide input conditions for other items such as spots, segments, tasks, data views, and activities. For example, events are used in some of these ways:   Record when customers click a spot on a web page or in a mobile app Collect data that is entered in a form Trigger the start of an customer journey activity Tracking user interactions is one of the core features that enables a brand to respond in real time to users based on their profile, origin, browsing behavior, and so on. When a visitor interacts with a website/app (for example, through a click event), that event is processed by the run-time environment and can be used to control many of branded site/app's features. The interactions that are monitored are the driving force behind many of the features that SAS Customer Intelligence 360 offers.   The Chapter 1 demo video below will be in the context of the retail industry. After a brief introduction, a customer journey will be exemplified beginning on the SAS Store website, and the behavioral trigger event will occur when a white wine product item is added to an ecommerce cart. We will pivot and show how the event was configured that will serve as the start to a series of targeted journey-based interactions.     Chapter 2: Behavioral Monitoring, Supervised Learning & Decisioning   Making the most of real-time customer interaction and streaming digital data requires real-time processing. Decisioning is best used to drive real-time actions in three contexts.   To drive the ideal next interaction that a customer or potential customer should have with your brand within their journey. As part of a cross-channel marketing initiative that unifies experience across customer-facing channels. To enable personalization that delivers customized messages based on visitor profiles or observed behaviors. SAS Intelligent Decisioning provides user access to a comprehensive set of ModelOps capabilities. SAS recognizes the importance of removing friction to activating sophisticated decisioning in martech, and released an embedded decisioning connector within SAS Customer Intelligence 360 in the July 2022 software release. Our vision is to provide brands with open access to rich digital data and sophisticated decisions using customizable business rules and real time analytical model calculations for timely insights and advanced personalization to accelerate conversions. Previously, users had to configure at least one agent in order to integrate with an external system. Now, the SAS Intelligent Decisioning native connector provides the ability to map SAS Customer Intelligence 360 data as inputs to published decisions through a no-code GUI.   With the connector configured, users can auto-trigger a decision based on customer behavioral events. Decision outputs are automatically made available to any SAS Customer Intelligence 360 supported channel/task (web, mobile app, email, etc.) for targeting and personalization. For example, you can invoke a published decision based on a user action (pageview, click or micro-goal achievement). Then you can use the customer outcome of that targeted decision (such as a next-best-experience recommendation) in a task or activity map for downstream personalization as that user's journey matures.   The Chapter 2 demo video below will pick up where Chapter 1 left off to show how sophisticated decisioning can assist in converting customer purchases.     Chapter 3: Offer Optimization, Reinforcement Learning & Contextual Bandits   Along with supervised and unsupervised learning, reinforcement learning is one of the major branches of machine learning. Each branch of machine learning differs from the other in the manner of feedback that the model receives during training. Supervised learning methods require data to be labeled. Labeled data enables supervised learning methods to compare the model’s output to the target output in order to improve the model. Supervised learning models are often used for prediction or classification tasks. Unsupervised learning methods do not require data to be labeled. Instead of comparing a model's output to a target, unsupervised learning methods look within unlabeled data to find useful patterns or groupings.   Reinforcement learning methods rely on a reward signal to train a policy. The reward signal is often a scalar function that indicates the goodness or badness of the agent’s decisions. Reinforcement learning models attempt to learn a policy that maximizes a long-term reward that is accumulated over a sequence of time steps. Despite the differences between unsupervised, supervised, and reinforcement learning, each learning method is complementary to the other. Each discipline plays a vital role in solving complicated tasks.   The use of a reward signal as a feedback mechanism leads to several unique qualities of reinforcement learning.   The reward signal enables learning to occur without the need for a supervisor. Therefore, when a method for determining a reward exists, an agent can learn directly from interactions with an environment. Learning by exploration enables an agent to gather its own data rather than rely on a supervisor to provide labeled input. Furthermore, an agent can explore without any prior knowledge of how an environment works, which might lead to superior performance. An agent’s observation of the environment at one instance of time is often highly correlated to its observation at the next instance. For example, consider a walking robot that receives as input a frame-by-frame video of its environment. Unless the robot is moving incredibly fast relative to the frame rate, each frame should be only a slight change from the previous frame. Because the RL agent’s input data is sequential, it is not independent and identically distributed. However, many traditional machine learning methods are suitable only for independent and identically distributed data.   Reinforcement learning methods can be grouped into two categories based on how the agent receives training data. In online reinforcement methods (online RL), an agent interacts with an environment, receives a reward, and updates its policy iteratively. Agent training occurs alongside data collection. In contrast, batch reinforcement learning methods (batch RL) decouples data collection from optimization. The separation of data collection from optimization enables batch RL methods to train an agent on a history of interactions with the environment.   SAS offers a variety of native reinforcement learning algorithms for users to leverage. The following table summarizes the main characteristics of each algorithm.   Algorithm Name Description Actor-Critic Policy gradient algorithm that learns the value function in order to compute the policy gradient by using the advantage function. Deep Q-Network (DQN) Q-learning algorithm that uses two neural networks to implement policy iteration. DQN uses experience replay to decouple correlated time-steps. Fitted Q-Network (FQN) Q-learning algorithm that uses two neural networks to implement policy iteration. FQN uses a fixed data set of experiences. REINFORCE Policy gradient algorithm that computes policy gradients by using sub-trajectory sampling with a baseline. REINFORCE-RTG Policy gradient algorithm that computes the policy gradient by using sampling with a baseline and accounting for causality.   If your brand develops personalization of customer experiences for your websites, mobile apps, email campaigns, etc., but reinforcement learning is a new/untested concept within your organization, contextual bandits can help. Using contextual bandits, brands can choose which content to display to the user, rank advertisements, select the best image to show on a screen, and much more. You can think about contextual bandits as an extension of multi-armed bandits, or as a simplified version of reinforcement learning.   In either scenario, the problem involves an exploration/exploitation tradeoff. Contextual bandits strike a balance between “exploration” (trying new tactics) and “exploiting” (presenting customers with the currently best-known tactic). This problem has many real-world applications, including website/app optimization, clinical trials, adaptive routing and financial portfolio design. In martech, you can think about it as smarter A/B testing.   Image 5: RL Contextual Bandits   A traditional multi-armed bandit algorithm typically found in martech software offerings that support testing outputs an action but doesn’t use any information about the state of the environment (context). For example, if you use a multi-armed bandit to choose whether to display puppy images or kitten images to the user of your website, you’ll make the same random decision even if you know something about preferences of the user. The RL contextual bandit extends this model by making the decision conditional on the state of the environment.   With such an approach, you not only optimize decisions based on previous customer observations, but you also personalize decisions for every situation. The algorithm observes a context, makes a decision, choosing one action from a number of alternative actions, and observes an outcome of that decision. An outcome defines a reward. The goal is to maximize average reward (not simply likelihood of conversion).   The final Chapter 3 demo video below will explain how SAS Customer Intelligence 360 and SAS Viya work together to enable upsell/cross-sell offers across multiple outbound channels using RL contextual bandits.     We look forward to what the future brings in our development process – as we enable marketing technology users to access all of the most recent SAS analytical developments. Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing here. ... View more

Over the last few years, brands have continued to explore and stress-test new mechanisms in deriving actionable analytical insight. An emerging trend that continues to garner attention orbits around trust which is critical when using analytics effectively. In this article, we will focus on the intersection of data and analytical literacy with how information is used to build models, how we accurately make model interpretations, and how we can elevate the confidence in an individual's ability to use algorithmic scoring to make intelligent decisions.   Our promise at SAS to help you overcome business problems is to gain deep customer knowledge that extends to action through seamlessly enhancing and extending customer data activation.    Image 1: Be There For Your Customers   Before jumping into the technology demo below, let’s ease in by addressing an important point. Digital transformation is now a top issue for most executives. It’s what unlocks the real-time insights and agility needed to deliver value to customers in the moments that matter. In reality, most real-time data is underused or not used at all. But few data processing systems are truly real time. Most systems capture real-time data in log files, then group events and batch process them to yield patterns that drive something close to real-time rules-based decision making. In other cases, insights from this data come weeks or months later – and in aggregate. Making the most of real-time customer interaction and streaming digital data requires real-time processing tools.   Decisioning is best used to drive real-time actions in three contexts.   To drive the ideal next interaction that a customer or potential customer should have with your brand within their journey As part of a cross-channel marketing initiative that unifies experience across customer-facing channels. To enable personalization that delivers customized messages based on visitor profiles or observed behaviors.   Image 2: Right AI, Right Time, Right Place   With that said, Let me propose a thought…   Is all AI built the same? No. Yet it seems every software vendor is pitching it. Let me be clear. It isn't enough to capture and store 1st/2nd/3rd/Zero-party customer data. Further, feeding this information into automated or custom prediction and segmentation models helps serve the marketer's mandate with accessible analytically-derived scores, but still falls short on potential.   Do you want to know what wedges separation for competitive advantage?  Decisioning engines enhanced with model governance, AI bias detection and supervised/unsupervised/reinforcement/deep learning insights triggered by real-time customer behavioral events contextualized by forward-thinking CDP capabilities. Think CDPs with a DataOps and ModelOps enablement mentality. If you take the time to lean in and look closely, it becomes obvious that all AI, ML & analytical solutions are not built the same.   Image 3: Run Lights Out, All The Time   The content shared in the technology demo below for the application area of customer next best experience represents an exciting opportunity to showcase technology and approaches across  SAS Customer intelligence 360  and  SAS Viya  for different profiles of users (marketers, analysts and data scientists) in the context of  customer analytics . While we attempt to maximize diversity, it should be noted a reasonable, non-exhaustive number of examples will be shared.     We look forward to what the future brings in our development process – as we enable marketing technology users to access all of the most recent SAS analytical developments. Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing   here . ... View more

The content shared in this article for the application area of propensity analysis represents an exciting opportunity to showcase technology and approaches across  SAS Customer intelligence 360  and  SAS Viya  for different profiles of users (marketers, analysts and data scientists) in the context of  customer analytics . While we attempt to maximize diversity, it should be noted a reasonable, non-exhaustive number of examples will be shared.     For readers interested in recent efforts by SAS to deliver automation of DIFM propensity analysis for our marketing software's users, please go here. This specific article will extend on automation with examples where SAS is accelerating analyst and data scientist workflows with the objective of performing customizable DIY propensity analysis.   To begin, SAS provides functionality without constraint through a no/low/high code software experience. Across the user spectrum, SAS enables DataOps, ModelOps & Customer Experiences. This includes, but is not limited to, data access, preparation, exploration, reporting, machine learning, AI, model management, decisioning and multi-channel journey orchestration. Our promise is to help users overcome business problems by gaining deep customer knowledge that extends to action by seamlessly enhancing the activation of customer data.    In the context of customer propensity analysis, SAS strives to provide:   Algorithms that produce better analytic scores and accuracy Automation of machine learning that aligns with greater productivity Embedded analytics, making AI more impactful and consumable Human-like interfaces, creating approachability Trust, which is critical when using propensity scoring effectively These concepts focus on how information & derived insight are used to make intelligent decisions regarding customer treatments, targeting and personalization.   Image 2: Customer propensity analysis principles in SAS   For every question a senior leader poses to their broader team, SAS delivers decision-oriented solutions that accelerate the timetable to actionability, as well as customizable modeling recipes and patented procedures that optimize the in-house AI talent your brand employs. Let’s gently walk through these capabilities through two demo examples.   The first demo will focus on a feature entitled Automated Prediction. This analysis object  runs several models on a response variable (or business outcome) that the user specifies. After specification, the remaining data items the user has access to are automatically added as underlying factors for auto-model construction. A champion model is chosen by the software, and the model prediction and the underlying factors are displayed. In other words, the software auto-builds an interactive summary report.   It is a frequent occurrence that SAS users desire performing propensity-based analysis through data visualization and interactive exploration. In other words, functionality that supports no- and low-code user profiles who benefit from a hybrid of automation and customizable features in completing their analyses.  But enough chatter, let's get on with the show!   Demo 1: DIY Customer Propensity Analysis Using Automated Prediction     How can we improve our conversion rate going forward? This is the question of the decade for analysts and data scientists, and I do not view your leadership team changing their interest in this topic any time soon. You can report, slice, dice, and segment away in your analytics platform, but needles in haystacks are not easily discovered unless we adapt. I know change can be difficult, but allow me to make the case for AutoML and   hyperparameter tuning   within the discipline of customer propensity analysis. A trendy subject for some, a scary subject for others, but my intent is to lend a practitioner's viewpoint.   Automated machine learning (commonly referred to as AutoML) involves automating the tasks that are required for building a predictive model based on machine learning algorithms. These tasks include data cleansing, feature engineering, variable importance, model selection and hyperparameter tuning, which can be tedious to perform manually. Platforms that provide this capability offer many benefits, such as empowering analysts by giving them a start at a machine learning workflow, as well as allowing data scientists to spend less time on model design and more time on making an AI-enhanced marketing campaign a reality.   Automation is not intended to replace the role of data scientists; ideally, there should be support for intervention in these systems to allow the performance of tasks such as domain-specific feature engineering, which can be a critical component of improving the performance of predictive modeling. These systems should be transparent with regard to the algorithms being used, so that users can be aware of, understand, and trust the insights being generated.   SAS provides different levels of automation that can be included in the machine learning pipeline-building process. Users can do any combination of automated tasks, such as having the system determine variable roles and levels, create the best transformation for numeric features, generate new features, and more. Alternatively, the entire process can be automated, through a graphical user interface as well as using a REST API.    With that said, I invite you to view a second demonstration that will address AutoML and hyperparameter autotuning with data captured and contextualized from SAS Customer Intelligence 360.   Demo 2: DIY Customer Propensity Analysis Using AutoML and Hyperparameter Autotuning     We look forward to what the future brings in our development process – as we enable marketing technology users to access all of the most recent SAS analytical developments. Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing   here.   ... View more

Fresh  reports  from Forrester Research released in Q2, 2022 on the subjects of customer analytics and real-time interaction management amplify the present day importance of brands exploiting DataOps and ModelOps in delivering precision within the modern practices of martech, targeting and personalization. In this article and video demonstration, we will cover:   The recent trend of new analytical techniques and automation coming together to reduce the effort brands need to exhibit to leverage algorithmic scoring in customer interaction management. Our perspective on missed opportunities in AI Marketing. Explain how SAS Customer Intelligence 360 enables users to execute machine learning  and action on the results of champion-challenger modeling pipelines to improve targeting intelligence on websites, mobile apps and more. Considerations for critical decisions in balancing marketing objectives between capturing conversions, improving efficiency and maximizing profit.   Image 2: Customer Interaction Optimization with Analytical Targeting     Before proceeding, the presence of a data science team is not a reality for some brands, and not a full stop solution for others. In the video demonstration below, we will highlight in detail how automation can assist in the challenge of targeting refinement without sacrificing considerations for meeting customizable objectives. Classification modeling, confusion matrices, classifier rules, cut off rates, and other analytical details represent an area of under-exploited potential in martech, and SAS is introducing a user experience that removes barriers in allowing brands to tap into the hype of   ModelOps .   Per the  Forrester Wave(TM): Customer Analytics Technologies, Q2 2022 r eport:   "Perhaps most importantly, SAS delivers cutoff recommendations for propensity models to optimize a decision — for example, identifying which customers to contact to optimize conversions while minimizing costs."   Analytical Targeting   is the latest feature from SAS Customer Intelligence 360 to automate the use of advanced machine learning enabled by the latest capabilities available from the   SAS Viya platform. We are ecstatic to share with you how it works.     We look forward to what the future brings in our development process – as we enable marketing technology users to access all of the most recent SAS analytical developments.    Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing   here. ... View more

The content shared in this article for the application area of segmentation represents an exciting opportunity to showcase technology and approaches across SAS Customer intelligence 360 and SAS Viya for different profiles of users (marketers, analysts and data scientists) in the context of customer analytics. While we attempt to maximize diversity, it should be noted a reasonable, non-exhaustive number of examples will be shared.   (Image 1: Technology user personas)     To begin, SAS provides functionality without constraint through a no/low/high code software experience. Across the user spectrum, SAS enables DataOps, ModelOps & Customer Experiences. This includes, but is not limited to, data access, preparation, exploration, reporting, machine learning, AI, model management, decisioning and multi-channel journey orchestration. Our promise is to help users overcome business problems by gaining deep customer knowledge that extends to action by seamlessly enhancing the activation of customer data.    (Image 2: Transform knowledge to action)     In the context of customer segmentation, SAS strives to provide:   Algorithms that produce better analytic scores and accuracy Automation of machine learning that aligns with greater productivity Embedded analytics, making AI more impactful and consumable Human-like interfaces, creating approachability Trust, which is critical when using segmentation effectively These concepts focus on how information & derived insight are used to make intelligent decisions regarding customer treatments, targeting and personalization.   Image 3: SAS for customer segmentation   Moving on, if the marketing & customer analytics market were a soccer game, we'd be in the second half. The first half was dominated by general-purpose toolkits that data scientists used to build custom models from scratch. Due to the scarcity of these data scientists, the martech ecosystem saw the emergence of solutions with prepackaged analytics geared towards marketers. Now we are in the second half of the game. The commoditization of many core analytical capabilities is well underway. But the game is far from over. SAS recognizes the critical importance of serving multiple enterprise personas.   This spectrum ranges from business users who want out-of-the-box analytics to savvy analysts who want to build models from scratch. It is extremely challenging for any brand or supporting vendor to predict if a do-it-yourself (DIY) approach vs. a do-it-for-me (DIFM) approach will be more effective. SAS constantly observes, accepts and uses this challenge to inspire our software’s design principles to enable capabilities to reflect the balancing needs between marketers, analysts and data scientists within an organization.   For every question a senior leader poses to their broader team, SAS delivers decision-oriented solutions that accelerate the timetable to actionability, as well as customizable modeling recipes and patented procedures that optimize the in-house AI talent your brand employs. Let’s gently walk through these capabilities through four demo examples.   The first demo will focus on a feature entitled Segment Discovery which supports SAS Customer Intelligence 360's testing capabilities. For example, when users desire to leverage A/B testing, they are ultimately comparing the conversion rates of two or more versions of a creative/message by tracking customer response rates. SAS adds value by auto-analyzing and determining at the conclusion of the test which variant led to the most conversions. In addition, SAS analyzes metric data to determine whether there are sub-segments of your target audience that respond better to a challenger variant rather than the winning variant.   Demo 1: DIFM Customer Segmentation Using Segment Discovery     It is a frequent occurrence that SAS users desire a segmentation solution that supports the analysis of customer, interaction, and contextual data through data visualization and exploration. In other words, users require features that support no- and low-code user profiles who benefit from a hybrid of automation and customizable functionality in completing their analyses. A few value propositions that we will demonstrate in Demos 2 and 3 below include:   Single-click auto-explanations which expose predictors & results for a customizable business outcome (or target variable) using C4.5 decision trees including the generation of relationship plots & high/low likelihood segments. Auto-unsupervised learning which determines the optimal number of clusters when performing K-Means by using the ABC method systematically. Parallel coordinate plots to provide users transparent interpretability in understanding segment profiles as well as portraying data stories for business presentations.   Demo 2: DIFM + DIY Customer Segmentation Using Automated Explanation     Demo 3: DIFM + DIY Customer Segmentation Using Visual Clustering     Across the supervised segmentation spectrum, data scientists have been pushing the boundaries with forests, gradient boosting, neural networks and other algorithms. However, practical internal business processes within brands frequently require typically require segment definitions through rules and analytical scoring. Let's explore a new user feature in SAS called Interactive Decision Trees for users who prefer the customization and power of model pipelining yet require flexibility to support their brand's unique segmentation deployment requirements.   Demo 4: DIY Customer Segmentation Using Interactive Decision Trees     We look forward to what the future brings in our development process – as we enable marketing technology users to access all of the most recent SAS analytical developments. Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing   here. ... View more

Over the last two years, brands continue to explore and stress-test new mechanisms in deriving actionable analytical insight. An emerging trend orbits around trust which is critical when using analytics effectively. This concept focuses on data/analytical literacy in how information is used to build models, accurate interpretation in models themselves, and confidence in an individual's own ability to use algorithmic scoring to make intelligent decisions. We are excited to announce that in the second quarter of 2022, SAS was recognized as a Leader in two influential reports released by Forrester Research relevant to the martech and business analytic industries.  The two topics of research represent key themes behind SAS Customer Intelligence 360. Wait a minute. What does this have to do with marketing technologies?  Allow me to focus your thinking.   Reality-tested AI to make confident decisions, at every moment It is encouraged to click on the reports below which provide readers free access to the research. The question I want you to consider after reviewing the content is:   Which software vendor has the strongest current offering across the totality of both research reports?     Forrester Wave(TM): Customer Analytics Technologies, Q2 2022    Forrester Wave(TM): Real-Time Interaction Management, Q2 2022   The hype of martech innovation in 2022 continues to soar, and every technology vendor is claiming to bolster the customer experience with machine learning & artificial intelligence. At the intersection of data, analytics, and marketing, detecting and acting on moments of significance between a brand and a customer matter. Is all AI built the same? No. Yet it seems every software vendor is pitching it. Let me be clear. It isn't enough to capture and store 1st/2nd/3rd/Zero-party customer data. Further, feeding this information into automated or custom prediction and segmentation models helps serve the marketer's mandate with accessible analytically-derived scores, but still falls short on potential.   Do you want to know what wedges separation for competitive advantage?  Decisioning engines enhanced with model governance, AI bias detection and supervised/unsupervised/reinforcement/deep learning insights triggered by real-time customer behavioral events contextualized by forward-thinking CDP capabilities. Think CDPs with a DataOps and ModelOps enablement mentality. Lean in and look closely, and it becomes obvious that all AI is not built the same.  Would you like a detailed example of what this means?  Per the  Forrester Wave(TM): Customer Analytics Technologies, Q2 2022 r eport:   "Perhaps most importantly, SAS delivers cutoff recommendations for propensity models to optimize a decision — for example, identifying which customers to contact to optimize conversions while minimizing costs."   The challenge for readers is clarifying what this actually looks like? Well, take a look here at a detailed presentation and demo on "Analytical Targeting" (the latest automated AI user feature released in SAS Customer Intelligence 360):     By leveraging SAS capabilities behind embedded functionality (or easy-buttons) within a marketer-centric designed user interface, the video above showed:   End-to-end automation of the data science workflow. Champion-challenger modeling tournaments for propensity score optimization. The execution and ranking of machine learning pipelines across Lift, Gain, ROC, etc. to auto-assign treatment, exclusion and control groups to identify high-value audience deciles within SAS Customer Intelligence 360 targeting capabilities. Moving on, remember when next-best-actions (NBA) were all the rage? Not anymore. Welcome to the era of next-best-experiences (NBX) expanding on the significant variance of approaches brands experiment with in personalizing products vs. offers vs. actions. Per the Forrester Wave(TM): Real-Time Interaction Management, Q2 2022 report:   "SAS differentiates by enabling its clients to fine-tune custom analytical models to ensure successful customer outcomes align with effective business operations. It applies its advanced analytics prowess to make NBX decisions for not only customer engagement but also operational use cases like risk and fraud management."   It's not enough to simply orchestrate a customer experience based on likelihood score or suppressions. We need to think bigger by activating and optimizing journeys using metrics like operational efficiency, profitability, and customer lifetime value (CLTV).You know where I'm going next. Let's exemplify transparently how SAS approaches decisioning during customer moments that matter. The storyline of this demo will be in a financial services context, and the next best experiences will highlight prioritization by expected customer value. We'll take this in two demo video steps. Let's begin with decisioning.     SAS Intelligent Decisioning provides user access to a comprehensive set of ModelOps capabilities. SAS recognizes the importance of removing friction to activating sophisticated decisioning in martech, and we are ecstatic to announce the release of our embedded decisioning connector within SAS Customer Intelligence 360 (July 2022 software release). Our vision is to provide brands with open access to rich digital data and sophisticated decisions using customizable business rules and real time analytical model calculations for timely insights and advanced personalization to accelerate conversions. Previously, users had to configure at least one agent in order to integrate with an external system. Now, the SAS Intelligent Decisioning native connector provides the ability to map SAS Customer Intelligence 360 data as inputs to published decisions through a no-code GUI.    Click on image to expand and view   With the connector configured, users can auto-trigger a decision based on customer behavioral events. Decision outputs are automatically made available to any SAS Customer Intelligence 360 supported channel/task (web, mobile app, email, etc.) for targeting and personalization. This feature enables users to exploit the advanced analytical capabilities of SAS Viya in SAS Customer Intelligence 360. For example, you can invoke a published decision based on a user action (pageview, click or micro-goal achievement). Then you can use the customer outcome of that targeted decision (such as a NBX recommendation) in a task or activity map for downstream personalization as that user's journey matures.   Click on image to expand and view   Per the  Forrester Wave(TM): Customer Analytics Technologies, Q2 2022 r eport:   "SAS’s product roadmap emphasizes additional UI simplification — a request the company has heard loud and clear from its clients. From a functionality perspective, SAS continues to blaze a trail with cutting-edge analytics. It recently added interactive decision trees for propensity modeling, enabling users to overlay business rules on top of classification models to make algorithmic insights work in a business context."   That is exactly what readers can expect from SAS going forward. Identifying and expunging areas of adoption challenge to connect innovation from data science for practical use cases brands are energized to unleash. This is the perfect pivot to our second demo video that focuses on model management, governance, bias detection and design. If trust is critical when using analytics effectively, this is the moment in the ModelOps process where projects lift off for success, or crash.     Per the Forrester Wave(TM): Real-Time Interaction Management, Q2 2022 report:   "Its roadmap promises to further democratize customer understanding, intelligent decisioning, and journey management for people of all skill sets. That’s welcome news to customer references, who award SAS this study’s only perfect reference rating for a vendor’s roadmap..."   We look forward to what the future brings in our development process – as we enable marketing technology users to access all of the most recent SAS analytical developments.    Learn more about how SAS can be applied for customer analytics, journey personalization and integrated marketing here. ... View more

Bintec aims to bring knowledge of technology and innovation trends to employees, clients and allies of Grupo Bancolombia with the support of expert organizations in the technology industry. For  13 years, this event has strengthened the Colombian technology community. Today, Bintec opens the doors to all the people in the world who want to connect to the fair and learn together with invited speakers about all the news and technological advances in the financial services and banking industry.   For the 2021 edition of the event, there were 10 trends or themes:   Cloud computing Blockchain Artificial intelligence Cybersecurity Voice interfaces and conventional robots Extended vision Virtual and extended reality Behavioral Internet Operations from anywhere Natural language processing   SAS was invited to speak on the themes related to AI and behavioral internet. In a session entitled "Digital Data Without Compromise", the agenda covered the capture of 1st party digital data, and how digital analytic technologies differentiate from one another. Recent martech industry trends revolving around data deprecation will shift common, well-adopted approaches. As inferred data gets harder to acquire, brands will prioritize their owned data assets to expand their customer and marketing analytic strategies.    Ultimately, the translation of this process can be represented by three components:   DataOps Artificial Intelligence ModelOps The breakout session is now available on-demand, and can be viewed below.     Learn more about how the SAS Platform can be applied for customer analytics, journey personalization and integrated marketing  here . ... View more

Let’s start by sharing a generalized definition for "digital analytics" platforms:   In short, they represent specialized analytic applications used to understand and improve digital channel user experience. Their focus ranges across customer acquisition and behavior, as well as optimizing marketing campaigns. The emphasis is on digital channels and techniques yet use cases can evolve to connect with offline data. They are end-to-end platforms performing functions from data collection through analysis and visualization.   It wasn’t long ago where brands operated across the customer lifecycle of acquisition, cross-sell, and retention using assumptions based on years of practitioner experience. Then up and coming analytic talent prior to the data science explosion began challenging those conventions with hard quantitative data. The shift to today is the monetary expenditures associated with capturing and storing 1st party digital data has decreased significantly opening a new realm of innovative possibilities.     Regarding the capture of 1st party digital data, if one doesn’t take a closer look into how digital analytic technologies differentiate from one another, it is easy to assume they do similar things. For example, both Google Analytics and SAS Customer Intelligence 360 can create new 1st party digital data sources for your brand to exploit. But is that it? No, and if one investigates this topic, it is evident that brands have incremental opportunities to generate business value and insight from their digital properties.    Recent martech industry trends revolving around data deprecation will dramatically shift common, well-adopted approaches to customer acquisition, upsell and retention. Now brands need to assess and potentially adapt their practices towards transparency and choice, value to the customer, and relationship depth. As inferred data gets harder to acquire, brands should prioritize their owned data assets and expand their customer and marketing analytic strategies. The availability and quality of your organization's 1st party data ingredients feeds directly into the potential of AI-based marketing and performance…cross-pollinating across multiple technologies enables a brand to leverage the unique strengths of multiple vendor solutions.   In this video we will discuss, explore and demonstrate the commonalities and differences between Google Analytics and SAS Customer Intelligence 360 in how they support modern customer and marketing analytic applications.     Learn more about how the SAS Platform can be applied for customer analytics, journey personalization and integrated marketing  here . ... View more

Rapid digital transformation over the past couple of years has resulted in a hybrid customer engagement model that is changing how brands shape, manage and deliver superior customer experiences (CX). Throw in the upcoming loss of the third-party cookie and marketers must double down on the data they do have: their own first-party data.   It wasn’t long ago where brands operated across the customer lifecycle of acquisition, cross-sell, and retention using assumptions based on years of practitioner experiences. Then up and coming analytic talent prior to the data science explosion began challenging those conventions with hard quantitative data. The shift to today is the expenditures with capturing and storing 1st party digital data has decreased significantly opening a new realm of innovative possibilities. For decades, SAS has been perceived as a technology that can flexibly absorb a variety of data sources. Now, SAS can help in the capture and creation of new 1st party digital data sources for your brand to exploit.    (Image 1: Capturing & Contextualizing 1st Party Digital Data)    Moving on, if the marketing & customer analytics market were a soccer game, we'd be in the second half. The first half was dominated by general-purpose toolkits that data scientists used to build custom models from scratch. Due to the scarcity of these data scientists, the martech ecosystem saw the emergence of solutions with prepackaged analytics geared towards marketers. Now we are in the second half of the game. The commoditization of many core analytical capabilities is well underway. But the game is far from over. SAS recognizes the critical importance of serving multiple enterprise personas.   This spectrum ranges from business users who want out-of-the-box analytics to savvy analysts who want to build models from scratch. It is extremely challenging for any brand or supporting vendor to predict if a do-it-yourself (DIY) approach vs. a do-it-for-me (DIFM) approach will be more effective. SAS observed, accepted and used this challenge to inspire our software’s design principles to enable capabilities to reflect the balancing needs between marketers, analysts and data scientists within an organization.   No matter what type of marketing or customer experience team you are a part of, there is likely a business leader is wrestling with a challenge. Typically, this translates into a question (or set of questions) that inspire research, projects or new assignments for others. Ultimately, the finish line is a decision. Because if a decision is never made, no value can be derived as a result.   Call it decision science, business analytics or marketing AI…it doesn’t matter. We need to exploit 1st party data to it’s fullest potential to answer the questions that keep senior leaders up late at night. Segmentation, recommendations, next-best-actions, attribution or prediction…we are all working on customer journey optimization.   The translation of this process between questions and decisions can be represented by three components:   DataOps Artificial Intelligence ModelOps   (Image 2: DataOps, AI & ModelOps)    SAS provides end-to-end capabilities across the entire bridge between questions and decisions. Through no-, low- and high code- interfaces, as well as support for multiple programming languages, access to these capabilities satisfies the needs of developers, data scientists, business analysts and marketers alike. For every question a senior leader poses to their broader team, SAS delivers decision-oriented solutions through AutoML and embedded analytics that accelerate the timetable to deployment, as well as customizable modeling recipes and patented procedures that optimize the in-house AI talent your brand employs. Let’s gently walk through these capabilities…     Learn more about how the SAS Platform can be applied for customer analytics, journey personalization and integrated marketing  here . ... View more

It’s amazing to realize that over a 100 years later, the old marketing lament “I know half of my marketing budget is wasted; I just don’t know which half” still rings true today for countless brands. Industry research covering B2C marketing decision-makers continues to harp on the challenge of measuring marketing results. Although many companies address this challenge with measurement and optimization tools, the immense amount of 1st party data awaiting to be harnessed remains under-exploited.     If you’re like me, you’ve grown fatigued and skeptical of the term AI constantly being used within martech industry presentations and vendor solution descriptions without clear explanation of its intent to solve business problems. So, let’s move past the buzz words and provide a definition for performance measurement.   It requires gathering data (and from our perspective, 1st party data specifically) about budgetary spend and campaign management tactics. After recording what your brand does, engagement metrics from consumers who have been targeted is the second piece of the puzzle. Subsequently, there are many methods to attribute conversions (whether those are sales, donations, subscriptions, etc.) using statistical analytic techniques.   The ultimate objective here is to quantify with clarity the financial impact of attributing marketing activities on performance. With that said, let’s take a moment to reflect on our new data-deprived marketing ecosystem. Data deprecation will dramatically shift common, well-adopted approaches to customer acquisition, upsell and retention. Now marketers need to assess and potentially adapt their practices towards transparency and choice, value to the customer, and relationship depth. Three areas for consideration include:   Building out zero- and first-party data assets - As inferred data gets harder to acquire, brands should prioritize their owned data assets and direct relationships with consumers. This includes collecting first-party interaction data as well as zero-party data — information that consumers volunteer about their preferences and interests, usually in exchange for a benefit or perk. From our experiences and customer projects here at SAS, it is extremely rare to see any type of data source out-perform 1st party data. In other words, 1st party data has always been and will continue to be king, and brands should double down on extracting customer insight from their owned data instead of trying to infer things like behaviors, context, and intent through sketchy tracking mechanisms.   Test alternative targeting approaches - The writing is on the wall for DMPs reliant on third-party cookies. Many brands have opportunities to invest deeper into the adoption of alternative approaches like first-party data-driven look-a-like models, segment-based audiences, or contextual targeting methods to connect relevant ads in higher performing touchpoints to specific audiences.   Expanding your marketing analytics strategy - Gone are the days of using cookie-based marketing attribution models to measure ad and touchpoint efficacy. But marketers don’t have to regress back to last-touch or heuristic measurement models. Customer identity data enables and maps out brand interactions & exposure across the journey as a foundation for people-based measurement. Additionally, by using campaign-specific contact and response data, as well as inbound interactions & targeted impressions, advanced measurement models can thrive.       The theme of rethinking customer identity translates to how brands should assess the impact of each data deprecation dimension on their current identity resolution strategy to understand their options for offsetting the loss of critical identity keys. The most likely scenario is that brands will need to adapt identity resolution processes and reconstruct a precise, scaled, and compliant identity graph. The availability and quality of your 1st party data ingredients feeds directly into the potential of AI-based marketing…   As insights evolve, and brands get smarter from data and analytics, when we think about touchpoint interactions, brands will always have a limited monetary budget creating competition between different marketing activities and touchpoints. Thus, the more a brand spends on one channel, the less it can spend on another.   Visualize a scenario where a customer receives a viewable impression of a display media ad, and then uses a search engine later that day to visit your brand’s website and make a purchase. Did the customer make the decision because they remembered seeing the ad? In another scenario, the customer receives a targeted email, and then receives impressions of an A/B test and targeted content of the website’s home page hero spot. In both cases, there is a question as to how much the first activity influenced the second and how to accurately measure this.     From a measurement perspective, weights of importance can be allocated to help marketers assess the impact of customer journey touchpoints and targeted interactions.  As the questions evolve with increasing sophistication, the focus adjusts back to diversifying the data. Attribution and performance measurement cannot be solved with traffic sources alone.  With more data, we can derive deeper insight from a greater level of granular detail regarding customer journeys.   What is happening when customers interact with your brand while they are on your website or mobile app? When they are interacting with your outbound communications like email… What are they doing? What signals are they sharing? These could be page views, the videos they are watching, the content they are downloading, the forms they are filling out, the time they are spending within certain categories of your customer experience.   By incorporating granular data signals like these into performance measurement, it will change the weighting of importance of journey-based traffic source originations and help increase the accuracy of explaining who is converting at a higher or lesser rate. For readers new to the subject of attribution and journey analysis, here is a recommended white paper.    Now, let's jump into the presentation and technology demo showcasing new attribution enhancements within SAS Customer Intelligence 360.     Learn more about how the SAS Platform can be applied for customer analytics, journey personalization and integrated marketing  here .   ... View more

Fresh research from Forrester released in Q2, 2021 on the subject of cross-channel campaign management amplifies the importance of brands exploiting 1st party data, machine learning, ModelOps and decisioning in delivering relevance and precision within the modern practices of customer targeting and personalization. Spanning across a variety of content, in this article and video demonstration, we will cover:   The recent trend of new analytical techniques and automation coming together to reduce the effort brands need to exhibit to leverage algorithmic scoring in interaction management. Our perspective on missed opportunities in AI Marketing. Explain how SAS CI360 enables users to execute supervised  machine learning  and action on the results of champion-challenger modeling pipelines to improve targeting intelligence on websites, mobile apps and more. Considerations for critical decisions in balancing marketing objectives between capturing conversions vs. maximizing efficiency.   (Image 1: Automation, ModelOps & Analytical Targeting)   Before proceeding, the presence of a data science or customer analytics team is not a reality for some brands, and not a full stop solution for others. In the video demonstration below, we will highlight in detail how automation can assist in the challenge of targeting refinement without sacrificing considerations for meeting customizable objectives. Classification modeling, confusion matrices, classifier rules, cut off rates, and other analytical details represent an area of under-exploited potential in martech, and SAS is introducing a user experience that removes barriers in allowing brands to tap into the hype of   ModelOps .   It's easy to recognize that every brand is customer obsessed, and each prospective interaction provides a potential opportunity to make an intelligent decision, deepen engagement and positively impact customer lifetime value. Analytical Targeting   is the latest feature from SAS CI360 to automate the use of advanced machine learning enabled by the latest capabilities available from the   SAS Viya platform. We are ecstatic to share with you how it works.     Learn more about how the SAS Platform can be applied for customer analytics, journey personalization and integrated marketing  here . ... View more

In this article and video demonstration, we will cover:   A customer experience in the context of hospitality, dynamic pricing and offer treatments. The demo story will be based on a fictitious hotel called SAS Hotel and a prospective customer is looking to book a stay at the resort property. SAS Customer Intelligence 360 will collect data from the consumer’s website activity, detect a specific interaction event of significance, and trigger a real-time call to SAS Intelligent Decisioning to obtain a recommended treatment driven by a combination of machine learning and business rules. After the customer experience demonstration, we will share transparent details on how the personalized treatments are derived and delivered.   Regardless if your brand uses one or multiple solutions to orchestrate communications across touchpoints, there is an opportunity to optimize interactions with target audiences over channels like web, mobile app, email, direct and more. The output of the insights derived from machine learning can specifically inform personalization strategies and treatments. As marketers, we want to provide offers that are both relevant to the customer and beneficial for the company.   Figure 1: Confident decisions at every moment   Machine learning and predictive analytics involve a variety of tasks, such as data cleansing, feature engineering, identifying variable importance, model selection and hyperparameter tuning, which can be tedious to perform manually. Although SAS offers many user benefits in accelerating towards the creation of analytical assets and IP through no-, low- and high code interfaces leveraging the SAS language, analysts who prefer Python or R are not excluded. Analysts can bring in open-source models into SAS, compare them with SAS models, govern and finally deploy through SAS.   Speaking about deployment. Although considered by many as the last phase of the analytical lifecycle, it is also one of the most important. What companies and brands expect from data scientists and marketing analysts is to get all these models in production. The connectivity of SAS Viya and SAS Customer Intelligence 360 showcases an end-to-end approach to monitor and evaluate modeling performance, create workflows to use these models according to specific business rules, and how we can expose these models for both batch and real-time use cases.   A key value proposition we want audiences to take away from this demo & presentation is the ability to use SAS Viya to build modeling projects leveraging SAS, Python, R or TensorFlow. As for the sub-topic of retraining modeling projects as needed, whether the model is from SAS or open-source, the customer experience has no patience for stale model scores and irrelevant treatments. SAS Model Manager ensures SAS Intelligent Decisioning continues to be relevant for personalization & targeting through system-driven champion model retraining or challenger model replacement due to drifting diagnostics of the model’s predictive precision, or feature importance.   The value proposition of any open-source or SAS analytical model assisting in the delivery of targeted treatments needs to ensure:   - The champion model and associated scoring is accessible via open Rest APIs - Deploy in-batch, streaming, cloud or edge devices - Support multiple publishing & container destinations - Monitor, detect and alert users or teams of model or feature degradation - Retrain the existing champion model as data refreshes over time, or replace the model entirely when a challenger begins performing better   It's easy to recognize that every brand is customer obsessed, and each prospective interaction provides a potential opportunity to make an intelligent decision, deepen engagement and positively impact customer lifetime value. With that said, let's jump into the presentation.     Learn more about how the SAS Platform can be applied for customer analytics, journey personalization and integrated marketing here.     ... View more

In this article and video demonstration, we will cover:   A customer experience in the context of financial services and consumer lending. The demo story will be based on a fictitious bank called SAS for Finance and a prospective customer is looking to apply for a loan by beginning a re-financing application. SAS Customer Intelligence 360 will collect data from the consumer’s website activity, detect a specific interaction event of significance, and trigger a real-time call to SAS Intelligent Decisioning to obtain a recommended treatment driven by a combination of machine learning and business rules. After the customer experience demonstration, we will share transparent details on how the personalized treatments are derived and delivered.   Regardless if your brand uses one or multiple solutions to orchestrate communications across touchpoints, there is an opportunity to optimize interactions with target audiences over channels like web, mobile app, email, direct and more. The output of the insights derived from machine learning can specifically inform personalization strategies and treatments. As marketers, we want to provide offers that are both relevant to the customer and beneficial for the company.   Figure 1: Confident decisions at every moment   Machine learning and predictive analytics involve a variety of tasks, such as data cleansing, feature engineering, identifying variable importance, model selection and hyperparameter tuning, which can be tedious to perform manually. Although SAS offers many user benefits in accelerating towards the creation of analytical assets and IP through no-, low- and high code interfaces leveraging the SAS language, analysts who prefer Python or R are not excluded. Open-source analysts can bring in open-source models into SAS, compare them with SAS models, govern and finally deploy through SAS.   Speaking about deployment. Although considered by many as the last phase of the analytical lifecycle, it is also one of the most important. What companies and brands expect from data scientists and marketing analysts is to get all these models in production. The connectivity of SAS Viya and SAS Customer Intelligence 360 showcases an end-to-end approach to monitor and evaluate modeling performance, create workflows to use these models according to specific business rules, and how we can expose these models for both batch and real-time use cases.   A key value proposition we want audiences to take away from this demo & presentation is the ability to use SAS Viya to build modeling projects leveraging SAS, Python, R or TensorFlow. As for the sub-topic of retraining modeling projects as needed, whether the model is from SAS or open-source, the customer experience has no patience for stale models and irrelevant treatments. SAS Model Manager ensures SAS Intelligent Decisioning continues to be relevant for personalization & targeting through system-driven champion model retraining or challenger model replacement due to drifting diagnostics of the model’s predictive precision, or feature importance.   The value proposition of any open-source or SAS analytical model assisting in the delivery of targeted treatments needs to ensure:   - The champion model and associated scoring is accessible via open Rest APIs (no matter whether the model originated from SAS, Python or R) - Deploy in-batch, streaming, cloud or edge devices - Support multiple publishing & container destinations - Monitor, detect and alert users or teams of model or feature degradation - Retrain the existing champion model as data refreshes over time, or replace the model entirely when a challenger begins performing better   It's easy to recognize that every brand is customer obsessed, and each prospective interaction provides a potential opportunity to make an intelligent decision, deepen engagement and positively impact customer lifetime value. With that said, let's jump into the presentation.     Learn more about how the SAS Platform can be applied for customer analytics, journey personalization and integrated marketing here.     ... View more