Reproduce “A Novel Multivariate Bi-LSTM model for Short-Term Equity Price Forecasting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Omkar Oak, Rukmini Nazre, Rujuta Budke, Yogita Mahatekar
This paper presents a Multivariate Bidirectional Long Short-Term Memory (Bi-LSTM) model for short-term equity price forecasting in the Indian stock market. The model incorporates OHLCV data along with selected technical indicators, demonstrating high accuracy in predicting next-hour stock prices with an average R-squared score of 99.4779% across NIFTY 100 companies.
Key insights
- Bidirectional processing consistently improves prediction accuracy by considering both past and future contexts in financial time series.
- The selective inclusion of technical indicators substantially enhances prediction accuracy, demonstrating their value beyond just OHLCV data.
- Multivariate models consistently outperform univariate models, underscoring the importance of incorporating diverse features for stock price prediction.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.