Nowadays stock market is the one of the major sources of raising resources for India and is act as a key driver for economic growth of a country. The stock market forecasting is a very difficult and highly complicated task because it is affected by many factors such as economic conditions, investor’s sentiments and political events etc. The stock market series are generally dynamic, nonparametric, noisy and chaotic by nature. Although many soft computing techniques have been widely used, Support Vector Machine (SVM) has gained its popularity and it has outperformed Artificial Neural Network (ANN) also.
Even though SVM is novel and performs best in many applications, the practicality of SVM is impacted due to the problems of choosing suitable parameters of SVM (C, σ and ε). The Cuckoo Search (CS) is based on the Swarm Intelligence optimization technique and is very simple to tune the parameters of SVM. The proposed hybrid CS-SVM technique has been proven to be able to generate better results when compared to ANN and SVM in the prediction of the stock price movement.