Advanced LSTM Neural Networks for Predicting Directional Changes in Sector-Specific ETFs Using Machine Learning Techniques

Trading and investing in stocks for some is their full-time career, while for others, it’s simply just a supplementary income stream. Universal among all investors is the desire to turn a profit. The key to achieving this goal is diversification. Spreading your investments across sectors is the key to profitability and maximizing returns. This study aims to gauge the viability of machine learning methods to practice the principle of diversification to maximize your portfolio returns. To test this, this study tests the Long-Short Term Memory (LSTM) model across 9 different sectors and upwards of $\mathbf{2, 2 0 0}$ stocks using Vanguard’s sector-based ETFs. Across all sectors, the R-squared value showed very promising results, with an average of $\mathbf{8 6 5 1}$ and a high of .942 with the VNQ ETF. These findings suggest that the LSTM model is a capable and viable model for accurately predicting directional changes among various industry sectors and can help investors diversify and grow their portfolios.