In monetary markets, it is mutually important and demanding to forecast the daily path of the stock market return. Among the some studies that focus on predicting daily stock market returns, the data mining measures utilized are either unfinished and not efficient, especially when a plethora of features are involved. This paper presents a whole and capable data mining process to anticipate the everyday direction of the S&P 500 Index ETF return based on 60 financial and economic features. To make it more accurate, I study many other techniques but SOP (Self Organizing Map) is a very proficient technique. To attain an accurate stock market prediction, the identification of the effective features is essential. In other words, the representative features of the factors play a key role in prediction efficiency. Technical and fundamental analyses are two indispensable tools in the financial market evaluation. Fundamental analysis can be used to estimate a firm’s performance and financial status over a period of time by carefully analyzing the institute’s financial statement. Technical analyses (TA), equally, evaluate securities by means of statistics such as past price and volume that are generated by market activities. The major analysis of TA is that it only reflects on the price movement and ignore the fundamental factors related to the company. The multiple classifier ensemble systems (MCS), a single type of machine learning technique, has newly become the focus of a new methodology for obtaining higher accuracy in predictions