Advanced deep learning framework for stock value prediction

Abstract

The main attractive feature to stock market is speedy growth of stock economic value in short yoke of time. The investor analyses the demonstration, estimated value and growth of organizations before investing money in market. The analysis may not be enough by using conventional process or some available methods suggested by different researches. In present days large number of stocks are available in market it is very difficult to study each stock by help of very few suggested foretelling methods. To know the anticipated stock value we need some advanced prediction technology for stock market. This paper introduce an advanced skillful method to plan and analyze the different organizers stock execution in market and prognosticate best suitable stock by predicting close price of stock. The projected arrangement is based on multilayer deep learning neural Network optimized by Adam optimizer. Recent 6 years (2010-2016) data of different organizations are applied to the model to demonstrate the skillfulness of the projected proficient method. From result it has been ascertained that the projected framework is best suited to all different data set of various sectors. The prediction error is very minimal as visible from outcome graph of framework.