STOCK MARKET TREND PREDICTION USING KNN

Abstract

Stock prices prediction is interesting and challenging research topic. Developed countries'
economies are measured according to their power economy. Currently, stock markets are
considered to be an illustrious trading field because in many cases it gives easy profits with lowrisk
rate of return. Stock market with its huge and dynamic information sources is considered as
a suitable environment for data mining and business researchers. In this project, we applied knearest
neighbor algorithm and non-linear regression approach in order to predict stock prices for
a company’s stock data to assist investors, management, decision makers, and users in making
correct and informed investments decisions. This algorithm uses the open, close, high, low
values of a stock in a day and volumes of that stock to train the module. Then for testing, an
opening value of the stock is taken from the user and given as test variable for the module. The
module will return the predicted closing value of that stock. The differences between actual and
predicted closing values of the stock can be interpreted using visualization graph plotted between
those two data. According to the results, the kNN algorithm is robust with small error ratio;
consequently, the results were rational and also reasonable. In addition, depending on the actual
stock prices data; the prediction results were close and almost parallel to actual stock prices.