Forecasting Restaurant Sales with the Sensitivity of Weather Conditions and Special Days Using Facebook Prophet

Abstract

This article focuses on forecasting sales for restaurant businesses using the Prophet model developed by Facebook. A method is proposed to make more accurate forecasts by accounting for the effects external factors have on sales, including weather conditions and special days. The analyses conducted on the real-time sales data of the daily operations of a restaurant business (provided by PROTEL Inc.) reveal that the Prophet model can forecast the sales of different products based on daily sales and weather data. The prediction performance of the model was evaluated using four error metrics: Mean Absolute Error, Mean Absolute Percentage Error, Mean Squared Error, and Root Mean Square Error. The results revealed that the model produced more consistent and accurate predictions for some product categories. This study, which aims to contribute to the literature through an optimization of operational efficiency and decision-making processes related to the restaurant industry, highlights the importance of external factors in sales forecasting in the restaurant industry and provides a detailed analysis of incorporating these factors into the forecasting process. The findings may support restaurant businesses in obtaining more accurate sales forecasts by taking external factors into account. In particular, understanding the effects of weather changes and special days on sales can contribute significantly to operational decisions in such areas as personnel planning and inventory management. In this regard, the article proposes innovative approaches to the challenges faced by restaurant operations, presenting different approaches found in the literature and a detailed model evaluation process.

Keywords

• Machine Learning
• Time Series Forecasting
• Facebook Prophet

References

1. Arunraj, N. S., & Ahrens, D. (2015). A hybrid seasonal autoregressive integrated moving average and quantile regression for daily food sales forecasting. International Journal of Production Economics, 170, 321-335. https:// doi.org/10.1016/j.ijpe.2015.09.037 google scholar
2. Badorf, F., & Hoberg, K. (2020). The impact of daily weather on retail sales: An empirical study in brick-and-mortar stores. Journal of Retailing and Consumer Services, 52, 101921. https://doi.org/10.1016/j.jretconser.2019.101921 google scholar
3. Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., Grobler, J., Layton, R., VanderPlas, J., Joly, A., Holt, B., & Varoquaux, G. (2013). API design for machine learning software: experiences from the scikit-learn project. arXiv preprint arXiv:1309.0238. google scholar
4. Jha, B. K., & Pande, S. (2021, April). Time series forecasting model for supermarket sales using FB-prophet. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 547-554). IEEE. https://doi.org/10.1109/ICCMC51019.2021.9418184 google scholar
5. Loureiro, A. L., Migueis, V. L., & Da Silva, L. F. (2018). Exploring the use of deep neural networks for sales forecasting in fashion retail. Decision Support Systems, 114, 81-93. https://doi.org/10.1016/j.dss.2018.08.009 google scholar
6. OpenWeatherMap. (2024). API documentation. OpenWeatherMap. Retrieved from https://openweathermap.org/api google scholar
7. Posch, K., Truden, C., Hungerlander, P., & Pilz, J. (2022). A Bayesian approach for predicting food and beverage sales in staff canteens and restaurants. International Journal of Forecasting, 38(1), 321-338. https://doi.org/10.1016/j. ijforecast.2021.02.008 google scholar
8. Ramos, P., Santos, N., & Rebelo, R. (2015). Performance of state space and ARIMA models for consumer retail sales forecasting. Robotics and Computer-Integrated Manufacturing, 34, 151-163. https://doi.org/10.1016/j. rcim.2014.12.001 google scholar

9. Shilong, Z. (2021, January). Machine learning model for sales forecasting by using XGBoost. In 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) (pp. 480-483). IEEE. https://doi.org/10.1109/ICCECE51280.2021.9342336 google scholar
10. Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37-45. https://doi.org/10 .1080/00031305.2017.1380080 google scholar
11. Thomassey, S. (2010). Sales forecasts in the clothing industry: The key success factor of the supply chain management. International Journal of Production Economics, 128(2), 470-483. https://doi.org/10.1016/j.ijpe.2010.07.007 google scholar
12. Tsoumakas, G. (2019). A survey of machine learning techniques for food sales prediction. Artificial Intelligence Review, 52(1), 441-447. https://doi.org/10.1007/s10462-018-9656-1 google scholar
13. Yusof, U. K., Khalid, M. N. A., Hussain, A., & Shamsudin, H. (2020, December). Financial time series forecasting using Prophet. In International Conference of Reliable Information and Communication Technology (pp. 485495). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-33582-3_42 google scholar
14. Zunic, E., Korjenic, K., Hodzic, K., & Donko, D. (2020). Application of facebook’s prophet algorithm for successful sales forecasting based on real-world data. arXiv preprint arXiv:2005.07575. google scholar