The present study is an attempt to forecast the prices of onion at Hubli market of Northern Karnataka, as the arrivals of Onion were found to be maximum in this market. The time series data on monthly price of onion required for the study was collected from the registers maintained in the Hubli APMC from year 1996-97 to 2010-11. The ARIMA model forecasted prices revealed an increase in the prices of onion in the future years and also demand for onion. Hence, farmers need to plan the production process in such a way that good price for the produce could be expected.  ARIMA model is an extrapolation method that requires only historical time series data on the variable under study. The Box-Jenkins model provides a verified approach for identifying and filtering most appropriate variations for the series being analyzed, for diagnosing the accuracy and the reliability of the models that have been estimated and lastly, for forecasting the price.