StockMem: An Event-Reflection Memory Framework for Stock Forecasting
By: He Wang , Wenyilin Xiao , Songqiao Han and more
Potential Business Impact:
Predicts stock prices by learning from past news events.
Stock price prediction is challenging due to market volatility and its sensitivity to real-time events. While large language models (LLMs) offer new avenues for text-based forecasting, their application in finance is hindered by noisy news data and the lack of explicit answers in text. General-purpose memory architectures struggle to identify the key drivers of price movements. To address this, we propose StockMem, an event-reflection dual-layer memory framework. It structures news into events and mines them along two dimensions: horizontal consolidation integrates daily events, while longitudinal tracking captures event evolution to extract incremental information reflecting market expectation discrepancies. This builds a temporal event knowledge base. By analyzing event-price dynamics, the framework further forms a reflection knowledge base of causal experiences. For prediction, it retrieves analogous historical scenarios and reasons with current events, incremental data, and past experiences. Experiments show StockMem outperforms existing memory architectures and provides superior, explainable reasoning by tracing the information chain affecting prices, enhancing decision transparency in financial forecasting.
Similar Papers
Advanced Stock Market Prediction Using Long Short-Term Memory Networks: A Comprehensive Deep Learning Framework
Computational Engineering, Finance, and Science
Predicts stock prices using computer learning.
Structured Event Representation and Stock Return Predictability
General Economics
Predicts stock prices better using news stories.
Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
Statistical Finance
Predicts stock prices better using news and AI.