Multi-period Learning for Financial Time Series Forecasting

ArXiv ID: 2511.08622 “View on arXiv”

Authors: Xu Zhang, Zhengang Huang, Yunzhi Wu, Xun Lu, Erpeng Qi, Yunkai Chen, Zhongya Xue, Qitong Wang, Peng Wang, Wei Wang

Abstract

Time series forecasting is important in finance domain. Financial time series (TS) patterns are influenced by both short-term public opinions and medium-/long-term policy and market trends. Hence, processing multi-period inputs becomes crucial for accurate financial time series forecasting (TSF). However, current TSF models either use only single-period input, or lack customized designs for addressing multi-period characteristics. In this paper, we propose a Multi-period Learning Framework (MLF) to enhance financial TSF performance. MLF considers both TSF’s accuracy and efficiency requirements. Specifically, we design three new modules to better integrate the multi-period inputs for improving accuracy: (i) Inter-period Redundancy Filtering (IRF), that removes the information redundancy between periods for accurate self-attention modeling, (ii) Learnable Weighted-average Integration (LWI), that effectively integrates multi-period forecasts, (iii) Multi-period self-Adaptive Patching (MAP), that mitigates the bias towards certain periods by setting the same number of patches across all periods. Furthermore, we propose a Patch Squeeze module to reduce the number of patches in self-attention modeling for maximized efficiency. MLF incorporates multiple inputs with varying lengths (periods) to achieve better accuracy and reduces the costs of selecting input lengths during training. The codes and datasets are available at https://github.com/Meteor-Stars/MLF.

Keywords: Multi-period Learning, Self-Attention Mechanisms, Patch Embedding, Financial Time-Series Forecasting, Redundancy Filtering, Equities (Stocks)

Complexity vs Empirical Score

• Math Complexity: 4.0/10
• Empirical Rigor: 8.0/10
• Quadrant: Street Traders
• Why: The paper focuses on practical deep learning modules (IRF, LWI, MAP, Patch Squeeze) for a real-world financial application (Alipay fund sales), and provides explicit GitHub links, datasets, and empirical metrics (MSE, consistency κ). While the mathematics involves standard transformer components and attention mechanisms, it lacks dense theoretical derivations or novel mathematical formalisms.

  flowchart TD
    subgraph Goal
        G["Research Goal<br>Enhance Financial TSF<br>for Multi-period Inputs"]
    end

    subgraph Methodology
        D["Multi-period Data<br>Inputs: Short/Med/Long Term"]
        M["Multi-period Learning Framework<br>MLF Modules"]
        M --> IRF["Inter-period Redundancy Filtering"]
        M --> LWI["Learnable Weighted-average Integration"]
        M --> MAP["Multi-period self-Adaptive Patching"]
        M --> PS["Patch Squeeze<br>Efficiency Module"]
    end

    subgraph Process
        P["Computational Process<br>Self-Attention & Integration"]
    end

    subgraph Outcomes
        F["Key Findings<br>Improved Accuracy & Efficiency"]
    end

    G --> D
    D --> M
    M --> P
    P --> F