In this column, AI strategist Dennie van den Biggelaar explains how to apply specific AI and machine learning to "advice in practice. Different editions will highlight the following topics:

• Starting with specific AI and ML

• Operationalizing in business processes

• Integrate into existing IT landscape

• Measuring = Learning: KPIs for ML

• Ethics, regulation and society

• AI and ML: a glimpse into the near future 

Logically, in this first edition, we start at the beginning: what is it and how do you start?

AI vs machine learning (ML)

AI is a machine or software that performs tasks that traditionally require human intelligence. Machine learning (ML) is a specific component* of AI that allows a machine or software to learn on its own from historical predictions or actions.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 a ready-made solution that you can use immediately, such as ChatGPT.

To build such an actionable AI solution, you have 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 predict it, what techniques to use and finally how to operationalize and secure it so that it actually leads to the desired results.

Example: customer attrition 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 likely to cancel their contracts. 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 insurance 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.You also need to consider your forecast horizon: how far ahead do you want to predict? Do you want to know which customers are going to cancel in the next 1, 3, 6, or 12 months? This may seem like a minor detail, but under the hood, it means you will be training a completely different ML model.

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 their subscriptions usually boils down to the fact 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 through 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?

Validating patterns

After the "machine" is put to work to find patterns, which can be used 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 costs him 15 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 others, the best ML model is determined. It is also possible to adjust algorithms more or less strict, so that they better fit 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 is the real 'AI' component, but more on that in the next edition! 

*AI is not always ML. For example, the algorithm Deep Blue (which defeated chess grandmaster Garry Kasparov) in 1997 is not ML, but it is AI. ML is always AI, though.

Dennie is an econometrician and has 12 years of experience designing, building and implementing machine learning solutions in the field. As co-founder and CTO of Onesurance , he is responsible for developing AI solutions and successfully operationalizing them with clients in the insurance industry.