COMPARATIVE STUDY ON RETAIL SALES FORECASTING BETWEEN SINGLE AND COMBINATION METHODS

Serkan Aras,İpek Deveci̇ Kocakoç,Cigdem Polat

doi:10.3846/16111699.2017.1367324

Abstract

In today’s competitive global economy, businesses must adjust themselves constantly to ever-changing markets. Therefore, predicting future events in the marketplace is crucial to the maintenance of successful business activities. In this study, sales forecasts for a global furniture retailer operating in Turkey were made using state space models, ARIMA and ARFIMA models, neural networks, and Adaptive Network-based Fuzzy Inference System (ANFIS). Also, the forecasting performances of some widely used combining methods were evaluated by comparison with the weekly sales data for ten products. According to the best of our knowledge, this study is the first time that the recently developed state space models, also called ETS (Error-Trend-Seasonal) models, and the ANFIS model have been tested within combining methods for forecasting retail sales. Analysis of the results of the single models in isolation indicated that none of them outperformed all the others across all the time series investigated. However, the empirical results suggested that most of the combined forecasts examined could achieve statistically significant increases in forecasting accuracy compared with individual models and with the forecasts generated by the company’s current system.

Highlights

Retail businesses are forced to use their resources efficiently and to make sound strategic decisions for the future in order to survive and increase their revenues, especially as conditions become ever more competitive
Sales forecasting is of great importance to companies making strategic decisions regarding their future investments
This study indicated that evolutionary neural networks produce more accurate forecasts than fully connected networks, and show still greater gains in accuracy over the seasonal autoregressive integrated moving averages (ARIMA) model in some cases

Summary

Introduction

Retail businesses are forced to use their resources efficiently and to make sound strategic decisions for the future in order to survive and increase their revenues, especially as conditions become ever more competitive. In order for any of these to be estimated, it is necessary first to predict the level of demand that will pertain in the market and, the company’s prospective sales. Market demand forecasts are a necessary precursor of all other estimates required by a given operation. Aras et al Comparative study on retail sales forecasting between single and combination methods and marketing) and facilitate them in reaching their targets (Mentzer, Bienstock 1998). Sales forecasting is of great importance to companies making strategic decisions regarding their future investments. Sales amounts are used in combination with margin forecasts to evaluate a company’s future income, and used together with turnover forecasts to assess a company’s future assets (Curtis et al 2014)

Objectives

Results

Conclusion