Risk of Transfer Learning and its Applications in Finance
This addresses the problem of selecting source tasks in transfer learning for finance applications, but it is incremental as it builds on existing transfer learning methods.
The paper introduces the concept of transfer risk to evaluate transferability in transfer learning, applying it to stock return prediction and portfolio optimization, with numerical results showing a strong correlation between transfer risk and performance.
Transfer learning is an emerging and popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. In this paper, we propose a novel concept of transfer risk and and analyze its properties to evaluate transferability of transfer learning. We apply transfer learning techniques and this concept of transfer risk to stock return prediction and portfolio optimization problems. Numerical results demonstrate a strong correlation between transfer risk and overall transfer learning performance, where transfer risk provides a computationally efficient way to identify appropriate source tasks in transfer learning, including cross-continent, cross-sector, and cross-frequency transfer for portfolio optimization.