Assessing the Impact of Microeconomic Factors on Indian Stock Prices: An LSTM-Based Deep Learning Approach to Price Prediction
Main Article Content
Abstract
This study investigates the impact of microeconomic factors on Indian stock prices and applies Long Short-Term Memory (LSTM) networks to forecast future price movements. A composite index, integrating critical economic indicators such as Gross Domestic Product (GDP) growth, inflation rates, interest rates, and unemployment, is developed to capture the influence of these variables on stock market trends. The data is normalized and weighted to create an index that reflects broader economic conditions, enabling a more holistic analysis of stock price dynamics. Historical stock price data is combined with this index to train the LSTM model, which is well-suited for handling time-series data due to its ability to identify long-term dependencies and patterns. Results indicate that microeconomic factors play a pivotal role in determining stock price fluctuations, and the LSTM model achieves high predictive accuracy. The integration of a composite index with deep learning offers a novel approach to understanding the interplay between economic indicators and market performance. This methodology provides valuable insights for investors seeking data-driven strategies and for policymakers aiming to evaluate the broader economic implications of stock market trends. By addressing a critical gap in the literature, this research highlights the potential of advanced machine learning techniques in financial forecasting. The findings underscore the importance of incorporating multiple economic indicators into predictive models, offering a robust framework for analysing complex market behaviours. Overall, this study establishes the efficacy of LSTM networks and composite indices in enhancing the precision of stock price predictions.