You’ve got ideas and tools. But are you ready to turn that spark into a proof-of-value project that gets the C-suite talking?   For data scientists, few opportunities match the focused intensity and creative freedom of a hackathon. These events provide a chance to test ideas, explore new tech, and collaborate across disciplines in a way that typical project timelines rarely allow. But here’s the catch: not every clever algorithm or slick demo survives the post-event post-mortem.   How, therefore, do you make your work matter? How do you go beyond “cool prototype” to “next business priority”? The answer is that you need to “hack smarter”. Here are some ideas to set you up for hackathon success.   Start with the problem, not the tech Hackathons are a playground for experimentation, but the best entries always start with a problem worth solving. Before diving into tools, think hard about the business value. Ask yourself who will benefit if this works, and how the world will be improved by solving this problem. Also consider how you will measure success.   Technically interesting solutions often fail to resonate because they lack a compelling use case. Framing your idea around a real-world pain point; preferably one that aligns with organisational priorities, gives your project a much higher chance of making an impact. One winning team from last year’s SAS Hackathon said their secret was “reverse-engineering business urgency into data science”. Keep that in mind.   Think minimum viable proof You won’t be able to build a whole product in a single hackathon. Instead, you need to focus on building proof. The best hackathon outputs are focused, scannable, and credible. They show enough to prove feasibility and spark interest, without trying to solve the whole world. Consider whether you can show a meaningful result in just one or two graphs, and identify the next step that would be needed.   Don’t over-engineer. Over-communicate.   Make Workbench your secret weapon Workbench provides the ability to rapidly experiment, visualise results, and collaborate across functions. This is a huge advantage, especially in the time-bound environment of a hackathon. Several teams last year used Workbench to share pipelines and visual outputs with business stakeholders in real time, blend structured and unstructured data quickly without jumping tools, and deploy containerised models that could be reused post-hackathon.   If you’re new to Workbench, it is worth investing some time upfront to get familiar with it. It could save you hours—and give your project the polish it needs to stand out.   Tell the story for the C-suite Think about your audience at the end of the hackathon. It might include product managers, department heads, or even C-level sponsors. Ask yourself what story you are telling. You need to explain why this, why now, and why you. One former participant said their biggest lesson was: “We won when we stopped thinking like developers and started thinking like communicators”. Your insights are powerful, but you need to show that to decision-makers.   Think beyond the hackathon Winning the hackathon would be great. Getting your idea adopted would be even better. Previous teams who have successfully managed this have identified internal champions early, and documented the process for handover or further development. Above all, though, they have seen the hackathon as a starting point, not a one-off event. As one team put it, “The hackathon gave us permission to explore but it was the follow-up that made the business case stick”.   Aim for collaboration Data scientists cannot win a hackathon by themselves. The best teams combine technical depth with design thinking, domain expertise, and great storytelling. If you’re assembling a team, think about diversity of perspective. If you’re joining a team, consider how you can contribute more than just code. How can you help shape the idea, validate it, or communicate its value?   Push the boundaries, but be prepared for failure too Hackathons are one of the few environments where speed and experimentation are the goal. You are not expected to build something perfect, only something possible. It is therefore worth pushing the boundaries, testing new techniques and exploring odd ideas. Some of the most promising innovations come from unexpected combinations and rapid iteration. It doesn’t matter if it doesn’t work, because you have still learned something.   Messy but intentional The best innovations do not arrive neatly packaged. They emerge from insight, creativity, and the freedom to explore. Hackathons give data scientists the chance to operate at full curiosity, full speed and full visibility. Following these tips will give your ideas the best chance to move beyond the walls of the hackathon and into the workflows of your organisation.   Bring your best ideas. Use the tools. Craft the story. And build for the future, not just to win.   Interested in learning more? Check out this on-demand webinar: Succeeding at SAS Hackathons - and Making the Move Beyond ... View more

Analytical Targeting is a feature soon to come to SAS Customer Intelligence 360 to apply machine learning methods to help decide the targeting of customers. I would like to walk you through a real-life example on how this feature creates value, but first, let me summarize the logic behind this feature.      The goal with Analytical Targeting is to target people who have the highest likelihood to convert based on the primary metric defined in a task (which is click-through by default). Targeting users who are most likely to convert improves the task conversation rate by excluding the members of the target audience who are unlikely to convert – and thereby freeing them up for other more relevant messages. The predictive models used in Analytical Targeting are built and deployed automatically with minimal input from the user.      There are two simple steps to deploying Analytical Targeting:      Enabling the modelling: Calculating the model scores starts. The model is not used yet.   The "model fitness" symbol will indicate the performance of the model so the users can decide whether to deploy the model or not.   Also, the "cumulative gains chart" is populated indicating the lift in conversions of the current model over the "baseline". The cumulative gains chart can help users select a cutoff threshold that corresponds to a desirable gain.   Active targeting: A cut-off is set, and the model scores are used to target users who are the most appropriate audience – i.e., more likely to convert.      The first step is to select the task that is likely to meet the prerequisites of Analytical Targeting feature which are:    Single experience task (standard web tasks and standard mobile tasks),  More than 50 conversions (less than this would not allow for a good enough model),   More than 5000 unique users who observed the task, and had previously visited within the last 28 days (to give behavioral data to build the model)    Now, let us see an example:     In our case, we see from the Performance tab of a web task that we have 19970 unique users in the last 25 days with 690 conversions. This gives us enough data to build the model:     After the feature is enabled from the Targeting task for the chosen task, once the prerequisites are met, the model will be built. Enabling the task is a simple button click:        Results of the model appear once the prerequisites are met. Then we can click on the “Edit” button to select the cutoff and activate (deploy) the model.          Activating the model is another simple exercise; clicking on the “Target users most likely to convert” button.     For example, here, the cut off is set for 30 percent and the model is automatically deployed. This means, only future visitors that score above the cut off will see this task.        Of course, the model performance can improve, and in this example, after 1 week, the model did, and we saw an increase lift from 119% to 140%.        As populations change, and visitors perhaps get more exposed to a task, or perhaps as tasks become less relevant, the model, and the model performance will change again.    Analytical Targeting is a feature in “test mode” at present, though it is available for suitable users that wish to test the feature for themselves. If you are interested learning more about it, here is a great article. Please get in touch with me, or your usual SAS Customer Intelligence 360 contact if you would like to know more about the feature.  ... View more