StockMem: An Event-Reflection Memory Framework for Stock Forecasting
This addresses the problem of noisy news data and lack of explicit answers in text for financial forecasting, offering incremental improvements in domain-specific stock prediction.
The paper tackles stock price prediction by proposing StockMem, an event-reflection dual-layer memory framework that structures news into events and tracks their evolution to extract market expectation discrepancies, resulting in superior performance and explainable reasoning compared to existing memory architectures.
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.