Do Deep Learning Models and News Headlines Outperform Conventional Prediction Techniques on Forex Data?

TL;DR

This study compares classical machine learning, deep learning, and news-based sentiment analysis for Forex prediction, finding simple models outperform deep learning and news features do not significantly enhance forecasts.

Contribution

It provides a comprehensive comparison of traditional, deep learning, and sentiment-based methods for Forex prediction, highlighting the limited impact of news headlines.

Findings

Classical models outperform deep learning models in Forex forecasting.

News headlines and sentiment features do not significantly improve prediction accuracy.

Word2Vec and SentenceBERT are effective text vectorization techniques.

Abstract

Foreign Exchange (FOREX) is a decentralised global market for exchanging currencies. The Forex market is enormous, and it operates 24 hours a day. Along with country-specific factors, Forex trading is influenced by cross-country ties and a variety of global events. Recent pandemic scenarios such as COVID19 and local elections can also have a significant impact on market pricing. We tested and compared various predictions with external elements such as news items in this work. Additionally, we compared classical machine learning methods to deep learning algorithms. We also added sentiment features from news headlines using NLP-based word embeddings and compared the performance. Our results indicate that simple regression model like linear, SGD, and Bagged performed better than deep learning models such as LSTM and RNN for single-step forecasting like the next two hours, the next day, and seven days. Surprisingly, news articles failed to improve the predictions indicating domain-based and relevant information only adds value. Among the text vectorization techniques, Word2Vec and SentenceBERT perform better.