Эффективность применения прогнозов волатильности в активных торговых стратегиях институциональных инвесторов на российском рынке акций

Фундаментальная и прикладная математика. 2026. Т. 26. № 3. С. 33–42.

Lysenok N.

This study examines the impact of realized volatility forecasts on the performance of active trading strategies in the Russian equity market. Using a sample of 17 liquid stocks over the period 2014–2026, a hybrid forecasting model is developed that combines HAR-J with gradient boosting; its superiority over the baseline HAR-J specification is confirmed by the Diebold–Mariano test (p < 0.001). Six directional strategies across three categories are tested with three mechanisms for integrating volatility forecasts and without them. The aggregation is performed sequentially at three levels: individual instruments, strategy portfolios across the 17 stocks, and multi-strategy portfolios (MSP). At the MSP level, a bootstrap procedure confirms a statistically significant increase in the Sharpe ratio when applying regime filtering (ΔSharpe = +1.19, p < 0.001) and volatility targeting (ΔSharpe = +1.22, p < 0.001). The MSP statistically significantly outperforms the IMOEX index (ΔSharpe = +2.05, p = 0.001) and maintains positive returns in all four years of the out-of-sample control period.

Keywords: машинное обучение, торговые стратегии, economic value, экономическая ценность, trading strategies, realized volatility, реализованная волатильность, machine learning, volatility targeting, multi-strategy portfolio, таргетирование волатильности, мультистратегийный портфель