SMU Data Science Review


In this paper, we compare demand forecasting methods used by the supply chain department at Bilports to open-source forecasting methods. The design and implementation of the open-source forecasting system also attempts to use several external datasets such as consumer sentiment, housing permit starts, and weather to improve prediction quality. Additionally, the performance of the forecast is evaluated by the reduction of shipment lead times from China, the company’s primary vendor. The objective of our paper is to improve Bilports’s forecasting capabilities. The primary motivation of this paper is to increase forecasting accuracy and identify the weaknesses of the methods used by the supply chain department. Our framework utilizes and compares both machine learning and statistical methods to generate a more cost effective and accurate forecast. We find that the modified open-source forecasting packages reduced the forecast error by 18 percent. Thus, the company’s ability to improve fulfillment rates and increase customer satisfaction.

Creative Commons License

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