Predicting Stock Prices with FinBERT-LSTM: Integrating News Sentiment Analysis

TL;DR

This paper introduces FinBERT-LSTM, a deep learning model that combines financial news sentiment analysis with stock price data to improve prediction accuracy, demonstrating superior performance over other models on NASDAQ-100 data.

Contribution

The paper presents a novel integration of FinBERT with LSTM architecture for stock prediction, incorporating news categories and market data for enhanced forecasting accuracy.

Findings

FinBERT-LSTM outperforms LSTM and DNN models in stock prediction.

Incorporating news categories improves model accuracy.

The model achieves the best results on NASDAQ-100 data.

Abstract

The stock market's ascent typically mirrors the flourishing state of the economy, whereas its decline is often an indicator of an economic downturn. Therefore, for a long time, significant correlation elements for predicting trends in financial stock markets have been widely discussed, and people are becoming increasingly interested in the task of financial text mining. The inherent instability of stock prices makes them acutely responsive to fluctuations within the financial markets. In this article, we use deep learning networks, based on the history of stock prices and articles of financial, business, technical news that introduce market information to predict stock prices. We illustrate the enhancement of predictive precision by integrating weighted news categories into the forecasting model. We developed a pre-trained NLP model known as FinBERT, designed to discern the sentiments within financial texts. Subsequently, we advanced this model by incorporating the sophisticated Long Short Term Memory (LSTM) architecture, thus constructing the innovative FinBERT-LSTM model. This model utilizes news categories related to the stock market structure hierarchy, namely market, industry, and stock related news categories, combined with the stock market's stock price situation in the previous week for prediction. We selected NASDAQ-100 index stock data and trained the model on Benzinga news articles, and utilized Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Accuracy as the key metrics for the assessment and comparative analysis of the model's performance. The results indicate that FinBERT-LSTM performs the best, followed by LSTM, and DNN model ranks third in terms of effectiveness.