Automated Hyperparameter Tuning for AI Marketing with SAS Customer Intelligence 360

[#1]

How can we improve our conversion rate going forward? The question of the decade for marketing analysts, and I do not view your leadership team changing their interest or focus 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 machine learning and hyperparameters within the discipline of customer analytics. A trendy subject for some, a scary subject for others, but my intent is to lend a practitioner's viewpoint.

To create a good machine learning or predictive model, many choices have to be made when deciding on algorithms and their parameters. The usual approach is to apply trial-and-error methods to find the optimal algorithms for the problem at hand. Often, an analyst will choose algorithms based on practical experience and personal preferences. This is reasonable, because usually there is no unique solution to create a machine learning model. Many algorithms have been developed to automate manual and tedious steps of the analytical process. Still, it requires a lot of time and effort to build a machine learning model with trustworthy results.

Figure 1: Machine learning, parameters and analyst choices

A large portion of this manual work relates to finding the optimal set of hyperparameters for a chosen modeling algorithm. Hyperparameters are the properties that define the model applied to a data set for automated information extraction.

In applications for marketing and customer analytics, an analyst must make many decisions during the training process. A large portion of the model building process is taken up by experiments to identify the optimal set of parameters for the algorithm. As algorithms get more complex (single-layer to multi-layer neural networks, decision trees to forests and gradient boosting), the amount of time required to identify these parameters grows.

There are several ways to support analysts in the cumbersome work of tuning model parameters. These approaches are called hyperparameter optimization, or auto tuning. Not only do ideal settings for the hyperparameters dictate the performance of the model’s training process, but more importantly they govern the quality of the resulting model.

In general, there are three different types of auto tuning methods: parameter sweep, random search, and parameter optimization.

1. Parameter sweep: This is an exhaustive search through a predefined set of parameter values. The analyst selects the candidates of values for each parameter to tune; trains a model with each possible combination; and selects the best-performing model. Here, the outcome very much depends on the experience and selection of the analyst.
2. Random search: This is a search through a set of randomly selected sets of values for the model parameters. With modern computers, this can provide a less biased approach to finding an optimal set of parameters for the selected model. Since this is a random search, it is possible to miss the optimal set unless a sufficient number of experiments are conducted, which can be computationally expensive.
3. Parameter optimization: This is the approach that applies modern optimization techniques to find the optimal solution. It's the best way to find the most appropriate set of parameters for any predictive model, and any business problem, in the least expensive way.

SAS provides analysts a hybrid, derivative-free optimization framework that operates in a parallel and distributed computing environment to overcome the challenges and computational expense of hyperparameter optimization. It consists of an extendable suite of search methods.

With that said, I invite you to view a video and technology demonstration that will address the following topics:

1. What is automated hyperparameter tuning?
2. What is the benefit for marketing-centric performance measures?

Learn more about how the SAS platform can be applied for marketing data management here.