# Solvency II Key Figures – Prediction and Explainability With Artificial Intelligence

Financial Mathematics and Machine Learning Support the Calculation of Solvency Capital

Our team supports insurance companies in solvency capital calculations by developing mathematical models and AI methods that are used to assess risks and calculate capital requirements under Solvency II. These methods, including machine learning and other innovative data analytics, help companies to ensure their financial stability and efficiently meet regulatory requirements in the market.

#### Solvency Capital Calculation: What is Solvency II All About?

The European supervisory regime Solvency II has been in force since 2016 – with the aim of preventing the insolvency of insurance companies and thus ensuring that they can fulfill their commitments even under extreme circumstances such as crises. Examples of such crises include natural disasters, stock market crashes or a high demand for health insurance benefits due to epidemics/pandemics. Solvency capital is calculated in different ways, whereby the calculating company must take into account all relevant risk scenarios in its internal model. The solvency ratio is a point of reference for the precautions taken by the insurance company. The solvency capital requirement (SCR) is a requirement that states that every insurance company must hold enough capital to cover its obligations so that it is still solvent after one year with a probability of 99.5%.

Two methods are currently available for calculating the SCR (Solvency Capital Requirement):

• Standard Formula: a highly simplified aggregation of the risks of the individual factors
• Internal Model: an internal model developed by the individual insurance company, a complete simulation that is accurate but usually not efficient and difficult to implement in terms of time

#### Valid Forecasts With Neural Networks: We Explain and Model Your Solvency II Data

We enable companies to analyze the sensitivity of their solvency capital in »real time«. Our research concept is based on a Machine Learning solution: a neural network is trained on existing data and the company's internal model. An exploratory Data Analysis identifies relevant drivers of equity, solvency capital and the solvency ratio.

We build a surrogate model based on Machine Learning as an additional, easy-to-evaluate replacement model for individual standard formulas or internal models. This makes it possible to explain past changes as well as to estimate, predict and analyze the future key figures of the respective company based on changes in market data and other parameters on a daily basis. By constantly and automatically learning new information, we ensure lasting improvement.

Artificial Neural Networks and probabilistic models such as Bayesian Neural Networks (BNN) offer the opportunity for a high level of explainability. The AI also indicates how confident it is in its predictions, and the possible effects of changes to selected risk factors are also shown directly.

The results are presented clearly in a dashboard. This is accessible via a dedicated app, which you can use via the browser on your intranet for the monthly updated estimates of basic own funds, the SCR and the solvency ratio. Company data remains internal and is not uploaded to a cloud.

#### PhD on Solvency Capital Calculation With Artificial Intelligence

We are working on numerous publications and analyses to continuously deepen our research and knowledge in this area and optimize our solutions. The ongoing work of our doctoral student Mark-Oliver Wolf, for example, has been investigating precisely these mathematical and Machine Learning aspects in the calculation of the solvency capital requirement since the end of 2023 under the heading »Mathematical and Machine Learning Aspects of the Solvency Capital Requirement Calculation«.

Prof. Dr. Ralf Korn is supervising the doctorate. He founded the »Financial Mathematics« department and headed it for many years. He contributes his in-depth expertise as a consultant and member of the Institute's Scientific Advisory Board.