MTMD: Multi-Scale Temporal Memory Learning and Efficient Debiasing Framework for Stock Trend Forecasting

2022-12-07

Social Science Research Network

AI Summary

Stock trend prediction faces challenges including difficulty in modeling multi-scale temporal dependencies, strong market noise, and the masking of genuine profit signals. To address these, we propose an end-to-end memory-augmented and bias-corrected framework. First, we introduce a novel learnable external attention memory module based on self-similarity, enabling dynamic long-range dependency modeling. Second, we design a graph neural network–driven adaptive fusion mechanism for heterogeneous global-local temporal features. Third, we establish a noise-robust multi-scale temporal consistency modeling paradigm, integrated with an efficient debiasing training strategy. Our method achieves significant improvements over state-of-the-art approaches across multiple benchmark datasets, simultaneously enhancing both prediction accuracy and profit stability. The source code is publicly available.

Abstract

The endeavor of stock trend forecasting is principally focused on predicting the future trajectory of the stock market, utilizing either manual or technical methodologies to optimize profitability. Recent advancements in machine learning technologies have showcased their efficacy in discerning authentic profit signals within the realm of stock trend forecasting, predominantly employing temporal data derived from historical stock price patterns. Nevertheless, the inherently volatile and dynamic characteristics of the stock market render the learning and capture of multi-scale temporal dependencies and stable trading opportunities a formidable challenge. This predicament is primarily attributed to the difficulty in distinguishing real profit signal patterns amidst a plethora of mixed, noisy data. In response to these complexities, we propose a Multi-Scale Temporal Memory Learning and Efficient Debiasing (MTMD) model. This innovative approach encompasses the creation of a learnable embedding coupled with external attention, serving as a memory module through self-similarity. It aims to mitigate noise interference and bolster temporal consistency within the model. The MTMD model adeptly amalgamates comprehensive local data at each timestamp while concurrently focusing on salient historical patterns on a global scale. Furthermore, the incorporation of a graph network, tailored to assimilate global and local information, facilitates the adaptive fusion of heterogeneous multi-scale data. Rigorous ablation studies and experimental evaluations affirm that the MTMD model surpasses contemporary state-of-the-art methodologies by a substantial margin in benchmark datasets. The source code can be found at https://github.com/MingjieWang0606/MDMT-Public.

Problem

• Predict stock market trajectory
• Capture multi-scale temporal dependencies
• Mitigate noise in stock data

Innovation

• Multi-scale temporal memory learning
• Efficient debiasing framework
• Graph network for data fusion