Abstract :

The Restaurant Industry Requires Substantial Investment, Yet A Significant Number Of New Ventures Fail Due To The Absence Of Reliable, Data-driven Revenue Prediction Methods. This Project Addresses The Challenge Of High-risk, Intuition-based Decisionmaking In Restaurant Expansion By Developing A Machine Learning Model To Forecast Annual Revenue. The Study Utilizes The Kaggle Restaurant Revenue Prediction Dataset, Which Consists Of 8,368 Records With 16 Features, Including Location Demographics, Cuisine Type, Seating Capacity, Marketing Budget, Social Media Presence, And Reservation Patterns. A Comprehensive Machine Learning Pipeline Was Implemented, Involving Exploratory Data Analysis, Data Preprocessing, Feature Engineering, And One-hot Encoding Of Categorical Variables. A Gradient Boosting Regressor With Optimized Hyperparameters—300 Estimators, A Learning Rate Of 0.05, And A Maximum Depth Of 4—was Trained To Model The Relationship Between Input Features And Revenue Output. The Model Demonstrated Outstanding Performance, Achieving An R² Score Of 0.9995, A Mean Absolute Error Of 4,611, And A Root Mean Square Error Of 5,862.

Published:

06-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1346-1354

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite