An approach to portfolio optimization with time series forecasting algorithms and machine learning techniques

The challenge of identifying suitable stocks for portfolio inclusion, particularly in the context of complex forecasting dynamics characterized by nonlinear time series and various influencing factors, is addressed study. To tackle this challenge, an approach combining the auto-regressive integrated moving average (ARIMA) and least-square support vector machine (LS-SVM) models is proposed for stock selection. Furthermore, mean-variance portfolio optimization model is utilized for optimal portfolio selection. The effectiveness this approach is demonstrated through comprehensive comparisons with alternative machine learning models, including support vector machines (SVM), LS-SVM, ARIMA, combined ARIMA+SVM models, and benchmarking models from the existing literature. Validation of the proposed technique is conducted historical data from the Bombay Stock Exchange (BSE), India.