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: predicting churn an office, you want to make sure that the right customers get the right attention from your advisors at the right time so that churn is minimized. It's ideal if you then know which clients have a high chance of canceling. But how do you translate this to the team?

It is common for a customer to cancel with a single policy. In most cases, this is simply a mutation and you don't want to pollute your ML model with this. Suppose a customer cancels with all policies within the main liability branch, but does not cancel the rest (yet). Is there then a customer in danger of leaving? And what if he also cancels everything within the main fire branch, but still has legal expenses and ORV? Have policies been transferred internally as well? How high is the churn ? All things you want to establish before you put 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 1, 3, 6 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.

Finding patterns

After you have clearly defined what you want to predict, it is time to see if your data is sufficiently Accurate, Available and Consistent (the 'data ABC') to do so. The main reason why customers cancel usually boils down, bottom line, to insufficient attention. The question, of course, is with whom, when and why 'too little attention' occurred. You don't have this information in your data warehouse, so you have to construct it yourself through feature engineering. Which features have a significant effect on the probability of churn? This is an analytical and creative process where knowledge and experience of insurance experts and data scientists come together.

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, a false prediction that someone is going to cancel next month (false positive) is not so bad. The advisor calls the customer and concludes that nothing is wrong: it just costs him 15 minutes of his time. If the algorithm wrongly predicts that someone will remain loyal (false negative), it is much more costly: 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?

Then you integrate the algorithm into the operational processes. How can the data get back and forth safely and efficiently, how can the advisor use the prediction easily? That's the work of data and software engineers. Finally, you also want the advisor to be able to give feedback on the quality of the algorithm, so the algorithm learns from the user. So the algorithm gets smarter and smarter and more efficient as it is used more.That is the real 'AI' component, but more on this 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.