ARIMA method is an extrapolation method for forecasting, and like any other such methods, it requires only the historical time series data for the variable under forecasting. ARIMA models are a-theoretical, implying that their construction and use are not based on any underlying theoretical model of the behavior of a variable. However, it does not require the investigator to choose the initial values of any variable and values of various parameters a priori. In this paper, an attempt has been made for estimating an ARIMA model for forecasting the inflation in Bangladesh, which is one of the important macroeconomic variables for determining monetary and fiscal policies of the government of Bangladesh. The time plots of actual values and the forecasted values are more or less coincided; hence it may be claimed that ARIMA (4, 12, 2, 0) model fits the inflation data of Bangladesh satisfactorily.

For any government, one of the most urgent economic issues is to stabilize the price and maintain a price level within the limits of purchasing power of the common people. High inflation is a long-standing problem in Bangladesh. There are many opinions regarding the proper reasons for inflation. Some researchers think that agricultural bottlenecks and successive balance of payment deficits are responsible for inflation. Another group thinks that in addition to these problems, expansionary monetary policy is the main culprit for inflation in Bangladesh. Whatever may be the reasons for inflation and its impact on the economy of Bangladesh, this paper tries to forecast the inflation of Bangladesh.

The main purpose for constructing a time series model is to forecast. Forecasting is a quantitative estimate about the likelihood of future events which is developed on the basis of past and current information. This information is embodied in the form of a model. By extrapolating models beyond the period over which they were estimated, one can make forecasts about future events. Such forecasts enable the policy makers to judge whether it is necessary to take any measure to influence the relevant economic variables. Data taken from the Central Bank of Bangladesh, Bureau of Statistics (BBS) is monthly in nature and covers from January 2007 to January 2011. Inflation is measured by CPI, with the base being 1995-96. For the construction of forecasting model, we use the data from January 2007 to October 2010, and the remaining data is used as out of sample period to check the strength of our prediction.

Bank Management Journal, Indian Banks, Asset Liability Management, Data Filtering, Least Absolute Deviation, Decision-Making Group, Commercial Banks, Ordinary Least Square, Banking Industry, Kenyan Banks, Least Squares Regression, Mutual Fund Industry, Linear Programming, Financial Markets, Capital Required Adequacy Ratio, Public Sector Banks.