Hybrid LSTM for NIFTY50 predictions
Stock market prediction using Long Short Term Memory Networks (LSTMs)
Aggregated NIFTY50 index data along with other global indices from various international stock markets, aiming to analyze the impact of global trends on the NIFTY50 index. Utilised statistics to develop technical indicators to capture market dynamics accurately.
Engineered a Hybrid LSTM model that incorporates Long Short-Term Memory networks to leverage temporal dependencies and the influence of global market trends on the NIFTY50 index.
The model was rigorously tested using advanced metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), and R2 score to ensure optimal performance. The goal was to accurately predict the NIFTY50 index’s movements by understanding its correlation with global market trends.
Achieved the goal of delineating the NIFTY50 index’s responsiveness to global market trends, resulting in a research paper that was presented at an IEEE conference, highlighting the project’s success in combining AI with financial analysis to forecast market movements effectively.