The Implementation Of Exponential Smoothing Technique In Forecasting Demands For SMI

Mohd Ridhwan, Mohd Jaih (2010) The Implementation Of Exponential Smoothing Technique In Forecasting Demands For SMI. Project Report. UTeM, Melaka, Malaysia. (Submitted)

	PDF (24 pages) The_Implementation_Of_Exponential_Smoothing_Technique_In_Forecasting_Demands_For_SMI_-_24_pages.pdf - Submitted Version Download (334kB)
	PDF (Full Pages) The_Implementation_Of_Exponential_Smoothing_Technique_In_Forecasting_Demands_For_SMI_-_Full_Pages.pdf - Submitted Version Restricted to Registered users only Download (2MB)

Abstract

Forecasting is the act of predicting future events or occurrences. In other word, forecasting is not only used in the industry but it can also be used to forecast events for daily life. In industry, forecasting is one of techniques that are used to predict demands from customers. This report represents an implementation of forecasting demands in Small Medium Industry (SMI). The forecasting technique selected for this research to predict the demands from customers is the exponential smoothing. These techniques have a weighted parameter to estimate the demands. The weighted parameter is called alpha (α). Besides that, the developed forecasting system is evaluated by finding the error produced from the outputs from the forecasting system. The errors are found by comparing the outputs from the forecasting system and the actual data collected. In this research, the Mean Absolute Percentage Error (MAPE) is used to calculate errors. The selection is due to the fact that this method is the most popular performance measure used in forecasting. In this research, a forecasting system had been developed successfully for predicting future demands for an SMI. The structure of the forecasting system consists of database management software and forecasting software. The forecasting software is developed based on the Exponential Smoothing technique. In order to evaluate the performance of the Exponential Smoothing based forecasting system, the outputs from the system had been compared with the outputs from Naïve method. Comparison between Naïve method and Exponential Smoothing shows that the Exponential Smoothing is the best method to be used because it provides consistently low error (MAPE) compared to Naïve method.

Actions (login required)

View Item