The best-known and most discussed example of ML software is ChatGPT, which is specifically designed to generate meaningful pieces of text for the user. However, there are countless other issues where machine learning can help us. However, there is not (yet) always an off-the-shelf solution that you can use right away, such as ChatGPT.

To build such an actionable AI solution, you need to bring the right competencies together at the right time. It is the job of an AI strategist to work with a multidisciplinary team of business experts, ML engineers, data engineers and data scientists to determine what you want to predict, how (accurately) to do it, what techniques to deploy and finally how to operationalize and secure it so that it actually leads to the desired results.

customer attrition

As an office, you want to be sure that the right customers receive the right attention from your advisors at the right time, so that customer attrition is customer attrition . It is ideal if you know which customers are most likely to cancel their subscription. But how do you communicate this to the team?

It often happens that a customer cancels a single policy. In most cases, this is simply a change and you don't want to contaminate your ML model with it. Suppose a customer cancels all policies within the main liability sector, but does not (yet) cancel the rest. Is this a customer who is at risk of leaving? And what if they also cancel everything within the main fire sector, but still have legal assistance and term life insurance? Have any policies been transferred internally? How high is customer attrition ? These are all things you want to determine before you set a team of ML engineers to work.

In addition, you need to consider your forecast horizon: how far ahead do you want to forecast? Do you want to know which customers are going to cancel in the next month or the next three, six or 12 months? Again, this seems like a detail, but under the hood it means that you are going to train a completely different ML model.

'Too little attention is the main reason customers cancel'

Finding patterns

Once you have clearly defined what you want to predict, it is time to check whether your data is sufficiently accurate, available, and consistent (the "data ABC"). The main reason why customers cancel is usually that they have not received enough attention. The question is, of course, who, when, and why there is "too little attention." This information is not stored in your data warehouse, so you will need to construct it yourself using feature engineering. Which characteristics (features) have a significant effect on the likelihood of customer attrition? This is an analytical and creative process that combines the knowledge and experience of insurance experts and data scientists.

Once a sound initial table of features has been sculpted, you can finally get started with machine learning. Experience shows that predicting royalties is best modeled with classification or survival analysis. There are hundreds of different ML techniques that are theoretically suitable for this purpose. In your choice, it is important to take into account: to what extent should the algorithm be explainable, how complex should the patterns be or how much data is ABC?

'Based on precision, recall and AUC scores , among others, the best ML model is determined'

Validating patterns

After putting the "machine" to work to find patterns with which to make predictions, there always comes an exciting moment... How accurate are the various models? For this, the ML engineer has an extensive toolbox. First, he keeps a portion of the data separate to test and validate a trained model. This guarantees the robustness of the patterns found and prevents a model from giving inaccurate predictions in the "real world. Then the false positives and false negatives are examined and what the costs are.

For example, an incorrect prediction that someone will cancel their subscription next month (false positive) is not so bad. The account managers the customer and concludes that there is no problem: it only takes him fifteen minutes of his time. If the algorithm incorrectly predicts that someone will remain loyal (false negative), this is much more expensive: you lose a customer.

Based on precision, recall and AUC scores , among other factors, the best ML model is determined. In addition, it is possible to tune algorithms more or less stringently to better suit the intended business process. This is called parameter tuning, and an experienced ML engineer knows how to do this responsibly.

How do you make it usable?

Next, you integrate the algorithm into the operational processes. How can the data be transferred back and forth in a secure and efficient manner, and how can account managers easily use account managers prediction? That is the job of data and software engineers. Finally, you also want account managers to be able to provide account managers on the quality of the algorithm, so that the algorithm learns from the user. The algorithm therefore becomes smarter and more effective the more it is used.

That's the real "AI" component, but more on that in the next issue!

The original article appeared in the VVP and is here to read online.