Yi Yang

Yi Yang

Oct. 30, 2026

Fintech, Quantitative investing, Deep learning, Multi-factor models, Volatility forecasting, Risk management.

Under the backdrop of rapid evolution in fintech, artificial intelligence technologies are fundamentally remodeling traditional quantitative investment and risk management models, leading to a new chapter of data-driven and intelligent financial markets. Based on the importance of accurately forecasting volatility as a key indicator for measuring risk levels and uncertainty in asset prices in financial markets as a guide for optimizing asset allocation and controlling risk. Traditional econometric volatility models are quite limited to work with high-dimensional, nonlinear financial data and also complex time-series dependencies. To overcome the shortcomings, this paper develops a framework for predicting financial market volatility and managing risk that combines multi-factor models with deep learning algorithms in the context of fin tech-enabled quantitative investing. With the Fama–French factor framework as its theoretical basis, this paper builds a multi-source set of financial features by fusing technical indicators and market behavior data and tests the validity of factors using IC-IR screen process. We propose a deep learning time-series model for jointly modeling market prices and volatility to capture the nonlinearities and long-term dependence structure of financial time series. We built a complete workflow of data preprocessing, model training and rolling forecasting using Python during model implementation, and systematically examined forecasting performance through multi-indicator evaluation system.

© 2026, the Authors. Published by ISCCAC

This is an open access article distributed under the CC BY-NC license