Algorithms to predict opening price and trading decision of stocks in Dhaka Stock Exchange

Abstract

One of the major tasks in stock market analysis is the discovery of specific events that give rise to a particular event. In this research we emphasize bin partitioning technique on a stock-oriented dataset with a time dimensional approach. We are mainly interested in bringing forward an algorithm for pattern discovery in sequential data streams and also bring out the interdependencies among the events. In our paper, we have proposed and implemented bin partitioning algorithm with real life data from Dhaka Stock Exchange as input. The prime task is of normalizing the data to bring about a form of uniformity among the data, so they could be useful in bringing about the correlation among the attributes in addition to the rules that suggest trading patterns. We also propose a model constructed using the nearest neighbour algorithm, whose main foundation lies behind the fact that stock event/data reflects its own behaviour along the time span. The result found in this research is encouraging enough and offers a new paradigm for stock market forecasting and trading decision about buy or sell a stock.