A FUZZY-BASED MODEL FOR FORECASTING STOCK PRICES

Abstract

Market creates an avenue for companies to seek capital for their various needs and also make profits. Forecasting of stock prices is regarded as a challenging task, as an accurate forecasting of stock prices may yield profits for investors. However, the stock market is rather a complicated system, and due to the complexity of stock market data, development of efficient models for forecasting is quite challenging. This Thesis adapted a Fuzzy-Based Model for short and long term investment in stock market. This rule based decision system will help traders to make correct decision at very low risk. Relative Strength Index (RSI), Moving Average Convergence Divergence (MACD), On-balance Volume (OBV) and Stochastic Oscillator (OS) are Technical Indicators used as inputs into Fuzzy Inference System. The fuzzy rules are a combination of the trading rules for each of the indicators used as the input variables of the fuzzy system and for all the four technical indicators used, the membership functions were also defined. Data was collected from Dangote Cement Plc for testing and evaluation of the model. The result is a recommendation to buy, sell or hold. This method reduces the risk factor considerably for both short term and long term investors when the output is compared with actual data from the Nigerian Stock Exchange. This system provides useful, accessible, reasonable and comprehensive information to aid investors to make good profits.