Media is loading

Date of Submission

Spring 4-24-2023

Project Type

Senior Design


Applied Statistics and Data Analysis


Industrial and Systems Engineering


Industrial and Systems Engineering

Committee Chair/First Advisor

Dr. Adeel Khalid


Family Restaurant is a local restaurant in the greater Atlanta area that serves a variety of dishes that include an assortment of 19 different proteins. Currently, Family Restaurant places protein orders based on business intuition, and tends to over-stock and sometimes under-stock. To minimize inventory costs by reducing over-stocking and preventing under-stocking of proteins, we applied Facebook Prophet (FB Prophet), ARIMA, and XG Boost machine learning models to predict protein demand and then fed these results into a Fixed Time Period inventory model to make an overall order suggestion based on the specified time period. We trained our models on sales data from 2021 and 2022 and tested our models on January 2023 data. Overall, FB Prophet shows a 6% savings per month from actual inventory spending, ARIMA shows a 34% savings, and XG Boost shows a 5% increase in spending for January 2023. ARIMA shows such high savings as it tends to under-stock in periods of high demand, while FB Prophet adequately meets periods of high demand and tends to over-stock during periods of normal demand. The restaurant prefers to over-stock, as under-stocking implies lost sales and thus, the loss of customer good faith, which is unacceptable for their business. Family Restaurant could adapt a hybrid approach of applying FB Prophet during known times of peak sales volume, while applying ARIMA during times of normal sales volume and realizing savings of 30%. The hybrid approach is slightly riskier, as it still relies on intuition. Ultimately, our recommendation is to follow the conservative approach of always applying the FB Prophet model and realizing savings at or around 6%.

Senior Design Poster.pptx (233 kB)
Senior Design Expo Poster

FDR Presentation.pptx (956 kB)
Final Presentation PowerPoint

Reducing Restaurant Inventory Costs Through Sales Forecasting.pdf (898 kB)
Final Design Report