There is an enormous increase in the number of food-serving establishments with the growing urbanization, which increases the challenges for government organizations in supervising their compliance with the food safety code. Food-borne illnesses could result in severe health and economic impacts and require efficient surveillance to ensure public safety and eliminate the negative impacts. This challenge can be addressed by applying data analytics in supporting the government supervision role.
The inspections conducted by the Government generate a huge amount of data that can be leveraged by data analytics and improve the efficiency of the operations and optimize the service provided by the municipal bodies. This project explores the use of Data Analytics methods in increasing the efficiency of food safety risk-based inspections of restaurants. A dataset from the New York City open data portal is used to apply data analytics, and machine learning (ML) methods and perform descriptive and predictive analysis. Data visualization and ML modeling is used to support predictions and decision-making related to public health monitoring of food- serving establishments.
The models’ objective is to predict the food-serving establishments that are prone to have critical violations and will not be compliant with the food safety checklist by classifying the restaurants into grades A, B, or C. Based on the predictive model, the inspections will be prioritized and scheduled for the inspectors to detect the restaurants with more critical violations first, which are classified as C, then B.
Results of my research show that the Extreme Gradient Boosting (XGBoost) model is the best model in classifying restaurants' grades in compliance with the food safety code, with an accuracy of 85.12 % compared to the Support Vectors Machines (SVM) model and the Random Force (RF) models.
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research (Dubai)
Khalil Al Hussaeni
Al Zarooni, Huda Amin, "Predicting food safety compliance for food-serving establishments inspections" (2023). Thesis. Rochester Institute of Technology. Accessed from