Saved in:
Bibliographic Details
Main Authors: Lyu, Fuyuan, Du, Linfeng, Weng, Yunpeng, Ying, Qiufang, Xu, Zhiyan, Zou, Wen, Wu, Haolun, He, Xiuqiang, Tang, Xing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.24835
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913945447563264
author Lyu, Fuyuan
Du, Linfeng
Weng, Yunpeng
Ying, Qiufang
Xu, Zhiyan
Zou, Wen
Wu, Haolun
He, Xiuqiang
Tang, Xing
author_facet Lyu, Fuyuan
Du, Linfeng
Weng, Yunpeng
Ying, Qiufang
Xu, Zhiyan
Zou, Wen
Wu, Haolun
He, Xiuqiang
Tang, Xing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24835
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Timing is Important: Risk-aware Fund Allocation based on Time-Series Forecasting
Lyu, Fuyuan
Du, Linfeng
Weng, Yunpeng
Ying, Qiufang
Xu, Zhiyan
Zou, Wen
Wu, Haolun
He, Xiuqiang
Tang, Xing
Machine Learning
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.
title Timing is Important: Risk-aware Fund Allocation based on Time-Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2505.24835