Student Name

Nada InamFollow

Degree

Master of Science in Data Science

Department

Department of Computer Science

Faculty/ School

School of Mathematics and Computer Science (SMCS)

Date of Submission

Fall 2024

Supervisor

Dr. Tariq Mahmood, Professor and Program Coordinator MS(CS) and MS(DS) Programs, School of Mathematics and Computer Science (SMCS)

Keywords

Demand Forecasting, Supply Chain, Inventory Management, Sales Forecasting

Abstract

Efficient demand forecasting is essential for profitability and sustainability in the retail food industry. This project focuses on developing a predictive sales model for a Pakistan-based retail food brand to overcome the limitations of manual forecasting methods, which often result in waste from overstocking, lost sales due to stockouts, and increased operational costs. Using sales data from five high-performing branches, a multiple linear regression model enhanced with dynamic subset feature selection was developed to predict daily donut sales with precision. The model achieved up to an 82% reduction in forecasting errors (RMSE) compared to traditional methods, demonstrating its ability to capture complex sales patterns that manual approaches often overlook. To ensure practicality and scalability, a web-based application was created, offering branch managers automated data integration, forecasting sales and actionable insights.

Document Type

Restricted Access

Submission Type

Research Project

The full text of this document is only accessible to authorized users.

Share

COinS