The Agency for Regulation and Development of the Financial Market of the Republic of Kazakhstan has updated its AFR econometric package with the OGPO Insurance Scoring Dataset. The dataset supports models that assess accident risk and score compulsory civil liability insurance policies for vehicle owners, with the aim of maintaining a portfolio payout ratio of about 70% while retaining customers. The risk-based approach is designed to raise premiums only for higher-risk drivers, while allowing lower-risk drivers to maintain or reduce their insurance costs. Available through the open PyPI and CRAN repositories, the dataset is intended primarily for risk managers, auditors and students. It is the package’s third dataset, extending its scope from corporate credit risk and macroeconomic analysis to insurance risk modeling.