联邦学习让金融预测在保护隐私的同时实现集体智能。
Federated Learning for Financial Forecasting
- 用共享LSTM模型，各机构仅交换更新不传原始数据。
- 联邦学习精度与集中训练相当，显著优于单方独立建模。
- 适合金融行业需隐私保护、数据异构的联合建模场景。
本文研究联邦学习（FL）在波动性金融市场趋势二分类中的应用。采用共享长短期记忆（LSTM）分类器，对比三种场景：(i) 基于全部数据合并的集中式模型，(ii) 单一机构基于本地数据子集的模型，(iii) 隐私保护的联邦协作，各参与方仅交换模型更新而不共享原始数据。进一步引入额外市场特征，刻意制造跨参与方非独立同分布（non-IID）数据，结合个性化联邦学习与差分隐私。数值实验表明，联邦学习在准确率与泛化能力上达到集中式基准水平，显著优于单一方模型。结果证明，在真实数据异构与个性化需求下，协同且隐私保护的学习仍能为金融领域带来可量化的集体价值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。