SMU Data Science Review


Forecasting demand is one of the biggest challenges in any business, and the ability to make such predictions is an invaluable resource to a company. While difficult, predicting demand for products should be increasingly accessible due to the volume of data collected in businesses and the continuing advancements of machine learning models. This paper presents forecasting models for two vodka products for an alcoholic beverage distributing company located in the United States with the purpose of improving the company’s ability to forecast demand for those products. The results contain exploratory data analysis to determine the most important variables impacting demand, which are time of year and customer. For each of the two products, models were built to predict demand for three major customers. For each product/customer combination, this paper compares time series and deep learning models to a naive model to see if the prediction accuracy can be improved. For five out of six products, the time series models reduced error by 2.5–66.7% compared to the naive models. Also, for one product, a hybrid CNN model developed for this paper outperformed the time series models by 3–10% and reduced error by 49% compared to the naive models.

Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License