Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Novel Multivariate Bi-LSTM model for Short-Term Equity Price Forecasting

Omkar Oak, Rukmini Nazre, Rujuta Budke, Yogita Mahatekar

TL;DR

This study tackles short-term stock price forecasting in the Indian market by developing a Bidirectional Multivariate LSTM (BiMLSTM) that incorporates 12 technical indicators alongside OHLCV features. Using hourly data from four NSE stocks across four sectors, the authors compare Univariate and Multivariate LSTM variants and demonstrate that the BiMLSTM with technical indicators delivers the highest predictive accuracy, achieving $R^2$ values around $0.993$–$0.997$ and low error metrics. The approach leverages a sliding-window formulation with $W=24$ and demonstrates robust performance across assets, underscoring the value of bidirectional context and feature enrichment for short-term trading decisions. These results suggest practical potential for real-time trading strategies and motivate extensions to longer horizons, additional markets, and broader feature sets including macroeconomic and sentiment signals.

Abstract

Prediction models are crucial in the stock market as they aid in forecasting future prices and trends, enabling investors to make informed decisions and manage risks more effectively. In the Indian stock market, where volatility is often high, accurate predictions can provide a significant edge in capitalizing on market movements. While various models like regression and Artificial Neural Networks (ANNs) have been explored for this purpose, studies have shown that Long Short-Term Memory networks (LSTMs) are the most effective. This is because they can capture complex temporal dependencies present in financial data. This paper presents a Bidirectional Multivariate LSTM model designed to predict short-term stock prices of Indian companies in the NIFTY 100 across four major sectors. Both Univariate LSTM and Univariate Bidirectional LSTM models were evaluated based on R2 score, RMSE, MSE, MAE, and MAPE. To improve predictive accuracy, the analysis was extended to multivariate data. Additionally, 12 technical indicators, having high correlation values with the close price(greater than 0.99) including EMA5, SMA5, TRIMA5, KAMA10 and the Bollinger Bands were selected as variables to further optimize the prediction models. The proposed Bidirectional Multivariate LSTM model, when applied to a dataset containing these indicators, achieved an exceptionally high average R2 score of 99.4779% across the four stocks, which is 3.9833% higher than that of the Unidirectional Multivariate LSTM without technical indicators. The proposed model has an average RMSE of 0.0103955, an average MAE of 0.007485 and an average MAPE of 1.1635%. This highlights the model's exceptional forecasting accuracy and emphasizes its potential to improve short-term trading strategies.

A Novel Multivariate Bi-LSTM model for Short-Term Equity Price Forecasting

TL;DR

This study tackles short-term stock price forecasting in the Indian market by developing a Bidirectional Multivariate LSTM (BiMLSTM) that incorporates 12 technical indicators alongside OHLCV features. Using hourly data from four NSE stocks across four sectors, the authors compare Univariate and Multivariate LSTM variants and demonstrate that the BiMLSTM with technical indicators delivers the highest predictive accuracy, achieving values around – and low error metrics. The approach leverages a sliding-window formulation with and demonstrates robust performance across assets, underscoring the value of bidirectional context and feature enrichment for short-term trading decisions. These results suggest practical potential for real-time trading strategies and motivate extensions to longer horizons, additional markets, and broader feature sets including macroeconomic and sentiment signals.

Abstract

Prediction models are crucial in the stock market as they aid in forecasting future prices and trends, enabling investors to make informed decisions and manage risks more effectively. In the Indian stock market, where volatility is often high, accurate predictions can provide a significant edge in capitalizing on market movements. While various models like regression and Artificial Neural Networks (ANNs) have been explored for this purpose, studies have shown that Long Short-Term Memory networks (LSTMs) are the most effective. This is because they can capture complex temporal dependencies present in financial data. This paper presents a Bidirectional Multivariate LSTM model designed to predict short-term stock prices of Indian companies in the NIFTY 100 across four major sectors. Both Univariate LSTM and Univariate Bidirectional LSTM models were evaluated based on R2 score, RMSE, MSE, MAE, and MAPE. To improve predictive accuracy, the analysis was extended to multivariate data. Additionally, 12 technical indicators, having high correlation values with the close price(greater than 0.99) including EMA5, SMA5, TRIMA5, KAMA10 and the Bollinger Bands were selected as variables to further optimize the prediction models. The proposed Bidirectional Multivariate LSTM model, when applied to a dataset containing these indicators, achieved an exceptionally high average R2 score of 99.4779% across the four stocks, which is 3.9833% higher than that of the Unidirectional Multivariate LSTM without technical indicators. The proposed model has an average RMSE of 0.0103955, an average MAE of 0.007485 and an average MAPE of 1.1635%. This highlights the model's exceptional forecasting accuracy and emphasizes its potential to improve short-term trading strategies.
Paper Structure (20 sections, 2 equations, 7 figures, 5 tables)

This paper contains 20 sections, 2 equations, 7 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Dataset
  5. Data Preprocessing
  6. Selection of technical indicators
  7. Normalization
  8. Technical Indicators
  9. Prediction models
  10. LSTM Cell Architecture
  11. Unidirectional LSTM
  12. Bidirectional LSTM
  13. Prediction Approaches
  14. Implementation and Results
  15. Evaluation Measures
  16. ...and 5 more sections

Figures (7)

  • Figure 1: List of All Technical Indicators
  • Figure 2: Data Description for ICICIBANK
  • Figure 3: Unidirectional LSTM Cell Architecture
  • Figure 4: Bidirectional LSTM architecture
  • Figure 5: Traditional approaches
  • ...and 2 more figures