Federated Learning for Financial Forecasting
It addresses the need for collaborative, privacy-preserving financial forecasting under realistic data heterogeneity, though it is incremental as it applies existing FL methods to this domain.
This paper tackles the problem of binary classification for volatile financial market trends using Federated Learning (FL) to enable privacy-preserving collaboration among agents, showing that FL achieves accuracy and generalization comparable to a centralized baseline while significantly outperforming single-agent models.
This paper studies Federated Learning (FL) for binary classification of volatile financial market trends. Using a shared Long Short-Term Memory (LSTM) classifier, we compare three scenarios: (i) a centralized model trained on the union of all data, (ii) a single-agent model trained on an individual data subset, and (iii) a privacy-preserving FL collaboration in which agents exchange only model updates, never raw data. We then extend the study with additional market features, deliberately introducing not independent and identically distributed data (non-IID) across agents, personalized FL and employing differential privacy. Our numerical experiments show that FL achieves accuracy and generalization on par with the centralized baseline, while significantly outperforming the single-agent model. The results show that collaborative, privacy-preserving learning provides collective tangible value in finance, even under realistic data heterogeneity and personalization requirements.