Comparison of Simple Moving Average, Single and Modified Single Exponential Smoothing

Abstract

Various forecasting algorithms have been investigated in various cases. Forecasting is an important activity, especially in the sales area. Accurate sales forecasting is a support system in increasing company turnover. The single exponential smoothing algorithm is one of the most commonly used forecasting algorithms, but its weakness is that the value of is chosen at random, despite the fact that the value greatly influences the accuracy of forecasting results. The selection of the value can be done by applying an optimization algorithm, such as the particle swarm optimization algorithm. The accuracy of the forecasting system is compared using single exponential smoothing method, single exponential smoothing method optimized by particle swarm optimization, and simple moving average algorithm in this study to find out a better method in forecasting, so it can be a suggestion for a company that will build a forecasting system. Based on the accuracy tests carried out using the MAPE and RSME measures, the best forecasting results were discovered by utilizing the single exponential smoothing method which was optimized with particle swarm optimization with an RMSE value of 1,222,701 and a MAPE of 21.86 %.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 28 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.