Abstract: A precise measure of corporate operating performance play critical role for achieving development during turbulent financial markets. This study proposes a reliable and sophisticated prediction architecture that incorporates risk metrics, dimensionality reduction technique, data envelopment analysis, and artificial intelligence technique for corporate operating performance forecasting. The securities market has deviated from its traditional form due to new technologies and changing investment strategies. The current securities market demands scalable machine learning algorithms supporting identification of market manipulation activities. In this paper we use Support Vector Machine algorithms to identify suspicious transactions in relation to market manipulation in stock market. The usage of ensemble classifiers in machine learning plays a vital role in prediction problems. The aim of this study is to analyze the accuracy of the ensemble methods in classifying the customers as good risk group or bad risk group. The opinions are judged on the basis of unsupervised and supervised learning. Supervised learning has unwavering to be superior to unsupervised mode of view verdict. The proposed paper has given a comparative study of naïve bayes and SVM on the opinions of the reviewers of the stock market. No system has been created for sentiment analysis in the share market. One decision in Stock Market can make huge impact on an investor life. The stock market is a complex system and often covered in mystery, it is therefore, very difficult to analyze all the impacting factors before making a decision. In this research we have tried to design a stock market prediction model which is based on different factors. To find best predicting model we can used the Support Vector Machine algorithm.
Keywords: risk management, classification, data mining, market manipulation, Support Vector Machine(SVM), Stock Market, Machine Learning, Feature Selection
|
DOI:
10.17148/IJARCCE.2018.7536
