Enhanced Multistep Prediction of Multivariate Market Indices Using Weighted Optical Reservoir Computing

We propose and experimentally demonstrate an innovative weighted optical reservoir computing system for market index prediction. By integrating fundamental market data with macroeconomic indicators and technical metrics, we capture the broader dynamics of the stock market. Our system shows significantly higher performance than the state-of-the-art methods such as linear regression, decision trees, and neural network architectures including long short-term memory. It effectively captures the market’s high volatility and nonlinear behaviors under limited data conditions, demonstrating strong potential for real-time, parallel, multi-dimensional data processing, and prediction.