Systemic financial risk prediction based on machine learning: the role of FinTech of different technical types

This study introduces a novel methodology for measuring a monthly FinTech index to address the timeliness challenges in systemic financial risk prediction using FinTech data. By employing machine learning models, the SHAP algorithm, and partial dependence plots, we assess the role of FinTech of different technical types as drivers of systemic financial risk. We simultaneously conduct comparative analyses of the predictive performance among traditional AR models, machine learning models, and ensemble forecasting models. The findings indicate that artificial intelligence, big data, and internet FinTech have the most significant influence on systemic financial risk, whereas IoT, cloud computing, and blockchain FinTech have a relatively limited impact. Regarding predictive performance, machine learning models generally outperform traditional AR models, with the K-Nearest Neighbors (KNN) model demonstrating particularly superior prediction accuracy and optimal robustness. Furthermore, three ensemble forecasting models (MEAN, MEDIAN, and TRIMMED MEAN) outperform individual machine learning models in terms of predictive performance. Notably, the impact of FinTech of different technical types on systemic financial risk exhibits diversified and nonlinear relationships, with significant variations in directional effects, sensitivity, and inflection points.