Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion

2026/03/08 by Pei-Jun Liao, Hung-Shin Lee, Yao-Fei Cheng +4 · 1 voice
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #Autoregressive integrated moving average #Filter (signal processing) #Machine Learning in Healthcare #Pooling #Stock (firearms) #Stock Market Forecasting Methods #Stock price #Time Series Analysis and Forecasting #Time series #cs.AI #cs.CL #cs.LG #q-fin.ST

paper · pdf · doi:10.48550/arxiv.2603.19286

openalex publication_date 2026/03/08 · arxiv published 2026/03/08 · arxiv updated 2026/03/08 · openalex created_date 2026/03/24 · openalex updated_date 2026/07/28

Abstract

Predicting stock prices presents challenges in financial forecasting. While traditional approaches such as ARIMA and RNNs are prevalent, recent developments in Large Language Models (LLMs) offer alternative methodologies. This paper introduces an approach that integrates LLMs with daily financial news for stock price prediction. To address the challenge of processing news data and identifying relevant content, we utilize stock name embeddings within attention mechanisms. Specifically, we encode news articles using a pre-trained LLM and implement three attention-based pooling techniques -- self-attentive, cross-attentive, and position-aware self-attentive pooling -- to filter news based on stock relevance. The filtered news embeddings, combined with historical stock prices, serve as inputs to the prediction model. Unlike prior studies that focus on individual stocks, our method trains a single generalized model applicable across multiple stocks. Experimental results demonstrate a 7.11% reduction in Mean Absolute Error (MAE) compared to the baseline, indicating the utility of stock name embeddings for news filtering and price forecasting within a generalized framework.

Citations

• StockTime: A Time Series Specialized Large Language Model Architecture for Stock Price Prediction
• The Llama 3 Herd of Models
• Deep Time Series Models: A Comprehensive Survey and Benchmark
• AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Prediction
• Ploutos: Towards interpretable stock movement prediction with financial large language model
• AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
• MASTER: Market-Guided Stock Transformer for Stock Price Forecasting
• Stock Movement and Volatility Prediction from Tweets, Macroeconomic Factors and Historical Prices
• A decoder-only foundation model for time-series forecasting
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• FinGPT: Open-Source Financial Large Language Models
• A Survey of Large Language Models
• BloombergGPT: A Large Language Model for Finance
• LLaMA: Open and Efficient Foundation Language Models
• One Fits All:Power General Time Series Analysis by Pretrained LM
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• A Survey of Forex and Stock Price Prediction Using Deep Learning
• A CNN-BiLSTM-AM method for stock price prediction
• Cross attentive pooling for speaker verification
• Self-attention encoding and pooling for speaker recognition
• Language Models are Few-Shot Learners
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Attention Is All You Need
• Bidirectional Attention Flow for Machine Comprehension
• Combining Technical Analysis with Sentiment Analysis for Stock Price Prediction
• Financial statement analysis and the prediction of stock returns
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Discussions

• Pei-Jun Liao, Hung-Shin Lee, Yao-Fei Cheng, Li-Wei Chen, Hung-yi Lee, Hsin-Min Wang: Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion https://arxiv.org/abs/2603.19286 h [bsky, 0 points, 0 comments]

Related

• Explainable Text-Driven Neural Network for Stock Prediction
• Leveraging Financial News for Stock Trend Prediction with Attention-Based Recurrent Neural Network
• Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks
• StockTime: A Time Series Specialized Large Language Model Architecture for Stock Price Prediction
• News Sentiment Embeddings for Stock Price Forecasting