2348. Leveraging RNNs, LSTMs, and Recurrence Quantification for Synchronization in the Indian Stock Market
Invited abstract in session WB-9: Algotrading and Market strategies, stream OR in Finance and Insurance .
Wednesday, 10:30-12:00Room: Clarendon SR 2.01
Authors (first author is the speaker)
| 1. | Charu Sharma
|
| Mathematics, Shiv Nadar Institution of Eminence | |
| 2. | Sanjay Sathish
|
| Shiv Nadar Institution of Eminence |
Abstract
Stock price synchronization is crucial for market dynamics, risk assessment, and portfolio management. Traditional correlation-based methods often fail to capture complex non-linear dependencies in financial markets. This research introduces a new approach for forecasting the synchronization of stock prices using machine learning and non-linear time-series analysis. To capture the complex non-linear relationships between stock prices, we utilize recurrence plots (RP) and cross-recurrence quantification analysis (CRQA). We utilize Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks to forecast the time series derived from Cross Recurrence Plot (CRP) data. Based on predefined thresholds, we then classify the predicted synchronization values into distinct categories, enabling both regression and classification analyses. We apply this methodology to a dataset of 20 highly capitalized stocks from the Indian market over a 21-year period. The findings reveal that our approach can predict stock price synchronization, with an accuracy of 0.98 and F1 score of 0.83. These results demonstrate that deep learning models trained on recurrence-based features can effectively capture synchronization patterns, offering valuable insights for algorithmic trading, portfolio diversification, and risk management in financial markets.
Co-author: Mr Sanjay Sathish (ss219@snu.edu.in)
Keywords
- Machine Learning
- Financial Modelling
- Forecasting
Status: accepted
Back to the list of papers