FORECASTING USD/INR EXCHANGE RATE USING SINGLE EXPONENTIAL SMOOTHING METHOD

Abstract

Exchange rate forecasts are necessary to evaluate the foreign denominated cash flows involved in international transactions. Thus, exchange rate forecasting is very important to evaluate the benefits and risks attached to the international business environment. The aim of this study is to forecast USD/INR exchange rate for Jan 2017- March 2017 using historic data for ten years from Jan 2007- Dec 2016 by time series analysis. The method used is Simple Exponential Smoothing method. Firstly, suitable data series is identified for applying exponential smoothing method by converting the data set into a stationary time series. Eviews 9 is used to apply exponential smoothing method to the data. The accuracy of this forecast is done using indicators like Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). After testing the model by forecasting values of year 2016, the model will be used to forecast the values of the first quarter of 2017. This study is purely based on technical analysis. Any deviations from the forecasted value may be attributed to fundamental factors that may influence the exchange rate like any changes in the current political system, changes in fiscal/monetary policies, GDP, inflation rate etc. In this study, few of the factors could be identified for the forecasted period and are explained in the analysis section.