An Empirical Analysis of Stock Market Price Prediction using ARIMA and SVM

Autoregressive Integrated Moving Average (ARIMA) model is the most acceptable and applied model in the terms of time series forecasting mechanism. Although, this model has its own kind of parametric limitations to capture the nonlinear patterns in the case of stock market prediction. Support vector machines (SVM) which is a novel neural network technique, can easily solve these problems which is available in the ARIMA model. Maximum number of the available reviewed paper and chapter has its own kind of limits as they concentrate on the particular application of financial market or explores machine learning tools and techniques that was applied on the particular dataset. This study will provide a comparative study of some relevant existing tools and the techniques applied in the area of the financial market analysis. The main aim of this study is: (i) a comparative study of the recent and relevant available model of the area, (ii) comparative study of ARIMA and SVM models in Rlanguage (iii) review of the fundamental challenges and futuristic challenges of the field.