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

TL;DR

The paper introduces MTMD, a novel model that captures multi-scale temporal dependencies and reduces noise in stock trend forecasting, significantly improving prediction accuracy over existing methods.

Contribution

The paper proposes a multi-scale temporal memory learning framework with an efficient debiasing mechanism, integrating a learnable embedding, external attention, and a graph network for enhanced stock trend prediction.

Findings

MTMD outperforms state-of-the-art models on benchmark datasets.

Ablation studies confirm the effectiveness of each component.

The model effectively captures multi-scale temporal dependencies and reduces noise interference.

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.