PREDICTIVE PURCHASE ORDER OPTIMIZATION IN A QUICK SERVICE RESTAURANT SUPPLY CHAIN

Abstract

In the fast-paced world of quick service restaurants (QSRs), managing inventory efficiently is vital for controlling costs and keeping operations smooth. Domino’s Pizza, like many QSRs, deals with ongoing challenges such as unpredictable demand, the risk of running out of stock, high costs of storing excess inventory, and the problem of wasting perishable ingredients. Traditionally, managers have made purchase decisions by relying on experience and historical sales averages—methods that don’t always account for changing consumer trends or seasonal spikes.This research explores how predictive analytics can make inventory management smarter and more cost-effective for Domino’s Pizza. By analyzing sales history and ingredient usage data, the research uses statistical and predictive tools to forecast demand and recommend what to order.The analysis demonstrates that data-supported forecasting improves order accuracy, reduces surplus inventory and waste, and enhances overall supply chain coordination. Notably, even relatively straightforward forecasting methods were sufficient to strengthen purchase planning within QSR operations. In the context of Domino’s operations, structured demand estimation contributes to better cost controlover inventory exposure and supports smoother day-to-day operations. From a financial standpoint, the study outlines a practical method for incorporating analytical tools into routine purchasing activities within food service organizations.