Stock price prediction using BERT and GAN

Abstract

The stock market has been a popular topic of interest in the recent past. The growth in the inflation rate has compelled people to invest in the stock and commodity markets and other areas rather than saving. Further, the ability of Deep Learning models to make predictions on the time series data has been proven time and again. Technical analysis on the stock market with the help of technical indicators has been the most common practice among traders and investors. One more aspect is the sentiment analysis -the emotion of the investors that shows the willingness to invest. A variety of techniques have been used by people around the globe involving basic Machine Learning and Neural Networks. Ranging from the basic linear regression to the advanced neural networks people have experimented with all possible techniques to predict the stock market. It's evident from recent events how news and headlines affect the stock markets and cryptocurrencies. This paper proposes an ensemble of state-of-the-art methods for predicting stock prices. Firstly sentiment analysis of the news and the headlines for the company Apple Inc, listed on the NASDAQ is performed using a version of BERT, which is a pre-trained transformer model by Google for Natural Language Processing (NLP). Afterward, a Generative Adversarial Network (GAN) predicts the stock price for Apple Inc using the technical indicators, stock indexes of various countries, some commodities, and historical prices along with the sentiment scores. Comparison is done with baseline models like -Long Short Term Memory (LSTM), Gated Recurrent Units (GRU), vanilla GAN, and Auto-Regressive Integrated Moving Average (ARIMA) model.

A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of Bitcoin

“…Combining the sentiment information extracted from BERT on carefully annotated Twitter data with stock OHLC price data, Dong, Yan, Almudaifer, Yan, Jiang and Zhou (2020) reported better results in terms of AUC for next-day price prediction compared to the state-of-the-art stock prediction model StockNet developed by (Xu and Cohen, 2018). Other similar work using BERT equally reported that their models outperformed others to various degrees (Sonkiya, Bajpai and Bansal, 2021;Chen, 2021). Based on these results, we have opted to use the state-of-the-art BERT model for this research, pretrained on a financial lexicon.…”

CBITS: Crypto BERT Incorporated Trading System

“…They showed that using the textual information significantly boosted the performance of intraday stock trading models. There were also studies using other approaches to incorporating sentiment features, such as Sonkiya et al [30], which leverages news sentiments from BERT and feeds these textual features to Generative Adversarial Networks [12], as well as Chen et el. [7], which makes use of contextualized embeddings generated from news headlines for price prediction.…”

Stock Broad-Index Trend Patterns Learning via Domain Knowledge Informed Generative Network

“…Faraz and Khaloozadeh [6] enhance GAN with wavelet transformation and z-score method in the data preprocessing phase. Sonkiya et al [45] generate binary sentiment score by FinBERT and employ GAN for stock price predictions. Such methods adapt Vanilla GAN which often suffers from mode collapse, and neglect possible driving factors such as complex public emotions, financial policies, and events, which limits the ability to achieve superior performance.…”