Neural Network for Volatile Stock Market Prediction
Samanyu Puri, Lokesh Kumar Shrivastav · International Conference on Computing for Sustainable Global Development · 2019
Stock businesses assume extremely critical and challenging part for the current society. Historical datasets of the few stock markets has been collected and used for this purpose. Then it will be trained and compared by the real data to check the deviation from the actuality of the model. From the last few years, specialists have tried to build a computationally efficient techniques and algorithms which predict and capture the nature of stock market. Maximum number of the available reviewed paper has its own kind of limits as concentrating on the particular application of financial market or explores machine learning tools and techniques which applied on the particular dataset. This paper will provide the comparative study of all tools and the techniques available in the recent machine learning frameworks and uses in the field of the financial market prediction methods. The main aim of this study is: (i) a comprehensive study of the available and recent literature in this area, (ii) Provide a generalized modeling for the stock market analysis and prediction (iii) review of the fundamental challenges of the field (iv)Realization of model by the use of fundamental Neural Network package available in R-language.