Do Deep Learning Models and News Headlines Outperform Conventional Prediction Techniques on Forex Data?
This work addresses Forex traders and researchers by showing that incremental improvements from news data are limited, with simple methods often better than complex deep learning for this domain.
The study compared classical machine learning and deep learning models, along with news headline sentiment features, for Forex market prediction, finding that simple regression models like linear, SGD, and Bagged outperformed LSTM and RNN for short-term forecasts, and news articles did not improve predictions.
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.