Realized Volatility Forecasting for New Issues and Spin-Offs using Multi-Source Transfer Learning
This addresses the problem of volatility forecasting for new financial assets with scarce data, which is incremental as it applies transfer learning to a known bottleneck in finance.
The paper tackles forecasting volatility for financial assets with limited historical data, such as new issues or spin-offs, by using a multi-source transfer learning approach that selects similar source data, and it shows this method outperforms models trained only on target or all data, with benefits seen from the first trading day.
Forecasting the volatility of financial assets is essential for various financial applications. This paper addresses the challenging task of forecasting the volatility of financial assets with limited historical data, such as new issues or spin-offs, by proposing a multi-source transfer learning approach. Specifically, we exploit complementary source data of assets with a substantial historical data record by selecting source time series instances that are most similar to the limited target data of the new issue/spin-off. Based on these instances and the target data, we estimate linear and non-linear realized volatility models and compare their forecasting performance to forecasts of models trained exclusively on the target data, and models trained on the entire source and target data. The results show that our transfer learning approach outperforms the alternative models and that the integration of complementary data is also beneficial immediately after the initial trading day of the new issue/spin-off.