Improved Fuzzy Forecasting Model for Stock Exchange Market

Stock price forecasting, which is an important topic in finance and economics, has prodded the enthusiasm of specialists throughout the years to develop models for better forecasts. Stock market is a key factor of monetary markets and signs of economic growth. Therefore, differ-ent forecasting models have been explored in literature for the stock data prediction. In this article, classical ARIMA model is mentioned and then Fuzzy Auto Regressive Integrated Moving Average (FARIMA) model is proposed as a new model. These two models are used for forecasting the stock exchange market of Attock cement Pakistan limited. Due to vague natures of stock data and parameter, fuzzy least square method is used in proposed FARIMA model. FARIMA model is based on the possibil-ity of success. These possibilities are defined by linguistic term, such as very low, low, average, high, and very high. This model makes it possible for decision makers to forecast the best based on fewer observations than the ARIMA model. Finally, comparison between the proposed model and ARIMA shows that the proposed model has better performance than ARIMA by using different criteria, such as mean squared error, mean ab-solute percentage error, and mean absolute deviation.