Applying Machine Learning Techniques to Forecast Demand in a South African Fast-Moving Consumer Goods Company

Authors

Martin Chanza¹ , Louise De Koker² , Sasha Boucher² , Elias Munapo¹ , Gugulethu Mabuza²

1. North-West University
2. Nelson Mandela University

Conference / event

6th International Conference on Intelligent Computing & Optimization 2023, April 2023 (Hua Hin, Prachuap Khiri Khan, Thailand)

Poster summary

Inventory planning is a critical function in FMCG companies, and forecasting plays a pivotal role in demand forecasting. The primary objective of this study was to compare the forecasting ability of statistical forecasting methods and machine learning models in demand forecasting in the FMCG sector. A case study approach was followed, using sales data from a specific category in a selected FMCG company for 2014-2019. Moving Average models, Seasonal Autoregressive Integrated Moving Average models and Artificial Neural Networks were used in this study. The results of this revealed that ANN model is more accurate in predicting demand in the FMCG sector. Forecasts from the ANN model showed an increasing trend in the sales of the supplements category. There is an increasing demand in baby products in the supplements category. For further research, we recommend using the Auto-Rforrressive Integrated Moving Average (ARIMAX) model for modeling demand when multivariate data is present.

Keywords

Machine Learning, SARIMA, Demand Forecasting, FMCG

Research areas

Business, Economics and Finance, Statistics

References

1. A. Dikshit, B. Pradhan, and M. Santosh, ‘Artificial neural networks in drought prediction in the 21st century–A scientometric analysis’, Appl. Soft Comput., vol. 114, p. 108080, Jan. 2022, doi: 10.1016/j.asoc.2021.108080

Funding

No data provided

Supplemental files

No data provided

Additional information

Competing interests

No competing interests were disclosed.

Data availability statement

The datasets generated during and / or analyzed during the current study are available from the corresponding author on reasonable request.

Creative Commons license

Copyright © 2023 Chanza et al. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.