Machine Learning for Advanced Predictive Risk Modelling 🇬🇧 🇪🇸

The development and implementation of risk models using machine learning enable immediate prediction of incidents and quantification of losses right before decisions and transactions are made. The ability to train predictive models and monitor their accuracy is highly sought-after in the job market as organizations rapidly adopt AI in risk management. These probabilistic models learn from real or synthetic incident data or correlations to detect emerging risk factors at any time.

In this hands-on workshop, you will explore polynomial regressions, vector machines, random forests, and Bayesian networks in use cases for operational and financial risks. A demo will show how to deploy a predictive model in Python to assess the risks of clients not renewing their contracts. You'll learn how to train and test a random forest algorithm to predict customer churn, even with incomplete or outdated customer data. This demo will offer valuable insights for retention strategies to mitigate revenue risks.

By the end of the workshop, you'll be inspired to identify concrete cases and machine learning approaches to automate risk assessments, enabling you to propose these innovative solutions to senior management looking to adopt AI.