Title: A comparative study of univariate time-series methods for sales forecasting

Authors: Vishvesh Shah; Stanko Dimitrov

Addresses: Department of Management Sciences, University of Waterloo, Waterloo, Canada ' Department of Management Sciences, University of Waterloo, Waterloo, Canada

Abstract: Firms use time-series forecasting methods to predict sales. However, it is still a question which time-series method a forecaster is best, if only a single forecast is needed. This study investigates and evaluates different sales time-series forecasting methods: multiplicative Holt-Winters (HW), additive HW, seasonal auto regressive integrated moving average (SARIMA) [a variant of auto regressive integrated moving average (ARIMA)], long short-term memory (LSTM) recurrent neural networks and the Prophet method by Facebook on 32 univariate sales time-series. The data used to forecast sales is taken from Time Series Data Library (TSDL). With respect to the root mean square error (RMSE) evaluation metric, we find that forecasting sales with the SARIMA method offers the best performance, on average, relative to the other compared methods. To support the findings, both mathematical and economic drivers of the observed performance are provided.

Keywords: sales time-series forecasting; SARIMA; long short-term memory; LSTM; comparison via root mean square error.

DOI: 10.1504/IJBDA.2022.126806

International Journal of Business and Data Analytics, 2022 Vol.2 No.2, pp.187 - 216

Accepted: 09 Aug 2022
Published online: 07 Nov 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article