2021/06/24 by Hengxu Lin, Dong Zhou, Lin, Hengxu +5 · 8 citations
Computer Science · Decision Sciences · Economics, Econometrics and Finance · Engineering · #Artificial intelligence #Computational Engineering #Computer network #Computer science #Data Stream Mining Techniques #Data mining #Database #Database transaction #Engineering #FOS: Computer and information sciences #FOS: Economics and business #Finance #Financial Markets and Investment Strategies #Machine Learning (cs.LG) #Machine learning #Router #Statistical Finance (q-fin.ST) #Stock (firearms) #Stock Market Forecasting Methods #Stock market #Stock trading #Transformer #and Science (cs.CE) #cs.CE #cs.LG #q-fin.ST
paper · pdf · doi:10.48550/arxiv.2106.12950
published in arXiv (Cornell University) (Cornell University) · Accepted by KDD 2021 (research track)
openalex publication_date 2021/06/24 · arxiv created 2021/06/25 · arxiv updated 2021/06/28 · openalex created_date 2021/07/05 · openalex updated_date 2026/08/08
Successful quantitative investment usually relies on precise predictions of the future movement of the stock price. Recently, machine learning based solutions have shown their capacity to give more accurate stock prediction and become indispensable components in modern quantitative investment systems. However, the i.i.d. assumption behind existing methods is inconsistent with the existence of diverse trading patterns in the stock market, which inevitably limits their ability to achieve better stock prediction performance. In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns. Essentially, TRA is a lightweight module that consists of a set of independent predictors for learning multiple patterns as well as a router to dispatch samples to different predictors. Nevertheless, the lack of explicit pattern identifiers makes it quite challenging to train an effective TRA-based model. To tackle this challenge, we further design a learning algorithm based on Optimal Transport (OT) to obtain the optimal sample to predictor assignment and effectively optimize the router with such assignment through an auxiliary loss term. Experiments on the real-world stock ranking task show that compared to the state-of-the-art baselines, e.g., Attention LSTM and Transformer, the proposed method can improve information coefficient (IC) from 0.053 to 0.059 and 0.051 to 0.056 respectively. Our dataset and code used in this work are publicly available: https://github.com/microsoft/qlib/tree/main/examples/benchmarks/TRA.