Timing is important: Risk-aware Fund Allocation based on Time-Series Forecasting

2025-05-30

AI Summary

Fund allocation in financial scenarios faces two key challenges: misalignment between forecasting and decision-making objectives, and propagation of prediction uncertainty into downstream decisions. To address these, we propose Risk-aware Time-Series Predict-and-Allocate (RTS-PnO), an end-to-end framework that jointly optimizes forecasting and risk-sensitive allocation without relying on parametric model assumptions. RTS-PnO employs differentiable modeling to ensure objective alignment throughout end-to-end training and introduces an adaptive uncertainty calibration module to mitigate uncertainty propagation. Evaluated across eight real-world time-series datasets—including money market funds, equities, and cryptocurrencies—RTS-PnO consistently outperforms state-of-the-art baselines. Furthermore, online A/B testing in Tencent’s cross-border payment system demonstrates an 8.4% reduction in regret, validating its practical efficacy in production environments.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Fund allocation has been an increasingly important problem in the financial domain. In reality, we aim to allocate the funds to buy certain assets within a certain future period. Naive solutions such as prediction-only or Predict-then-Optimize approaches suffer from goal mismatch. Additionally, the introduction of the SOTA time series forecasting model inevitably introduces additional uncertainty in the predicted result. To solve both problems mentioned above, we introduce a Risk-aware Time-Series Predict-and-Allocate (RTS-PnO) framework, which holds no prior assumption on the forecasting models. Such a framework contains three features: (i) end-to-end training with objective alignment measurement, (ii) adaptive forecasting uncertainty calibration, and (iii) agnostic towards forecasting models. The evaluation of RTS-PnO is conducted over both online and offline experiments. For offline experiments, eight datasets from three categories of financial applications are used: Currency, Stock, and Cryptos. RTS-PnO consistently outperforms other competitive baselines. The online experiment is conducted on the Cross-Border Payment business at FiT, Tencent, and an 8.4% decrease in regret is witnessed when compared with the product-line approach. The code for the offline experiment is available at https://github.com/fuyuanlyu/RTS-PnO.

Problem

• Optimizing fund allocation using time-series forecasting
• Addressing uncertainty in financial prediction models
• Aligning prediction and optimization goals end-to-end

Innovation

• Risk-aware Time-Series Predict-and-Allocate framework
• End-to-end training with objective alignment
• Adaptive forecasting uncertainty calibration