Teaching Learning Based Optimized Support Vector Regression Model for Prediction of Indian Stock Market

  • Ankita Singh, Jatindra Kumar Dash, Biswajit Behura, S. Chakravarty


The accurate prediction of financial market prices is highly important for making crucial investments with the least amount of risk. With regard to complex financial data resulting due to several factors that may be political or economic, machine learning and evolutionary computation techniques have been implemented by various authors for financial time series forecasting. Particle Swarm Optimization (PSO) and Teaching Learning Based Optimization (TLBO) algorithms have been implemented independently to optimize the parameters of many forecasting models. This paper presents the comparison between two hybrid Support Vector Regression (SVR) models to predict future Indian stock market price. In particular a PSO-optimized SVR model along with a TLBO-optimized SVR model was developed and the results yielded by both were studied. The proposed PSO-SVR model is based on the natural flocking behavior shown by birds and fish to get to the food source.  The proposed TLBO-SVR model, inspired from the knowledge transfer occurring between a teacher and students in a classroom, is a parameter-less optimization algorithm that avoids any algorithm-specific parameter that is to be provided by the user during optimization. Regression metric – Root Mean Squared Error (RMSE) is used as Fitness function for both optimization algorithms. The efficiency of both the hybrid models was calculated by predicting the daily closing prices of S&P BSE SENSEX index traded in the Bombay Stock Exchange of India. Metrics such as Normalized Mean Squared Error (NMSE), Root Mean Squared Error (RMSE), Directional Symmetry (DS) and Mean Absolute Error (MAE) were used to find the performance of both models. The comparison of the experimental results shows that both hybrid models are effective and perform far better than the standard SVR model. It is noticed that even though TLBO algorithm yields slightly better results, PSO is better compared to others with respect to time taken for optimization and delivering optimized parameters fast enough.

Keywords: Support Vector Regression (SVR), Particle Swarm Optimization (PSO), Teaching Learning Based Optimization (TLBO), Financial Time Series Forecasting, Indian Stock Market.

How to Cite
Ankita Singh, Jatindra Kumar Dash, Biswajit Behura, S. Chakravarty. (2020). Teaching Learning Based Optimized Support Vector Regression Model for Prediction of Indian Stock Market. International Journal of Advanced Science and Technology, 29(05), 3002 - 3015. Retrieved from http://sersc.org/journals/index.php/IJAST/article/view/11600