Smart Compliance: A Supervised Learning- Based Classification of Clients Dress Code for Policy Enforcement in Philippine Government Offices

Dress code compliance is an essential aspect of professional conduct, particularly in format settings such as Philippine government offices. This study, Smart Compliance: A supervised Learning -Based Classification of Clients Dress Code for Policy Enforcement in Philippine Government offices, explores the application of supervised machine learning classification to assess whether individuals adhere to the prescribe dress code policies. Using support vector machine (SVM), the research aims to develop model capable of classifying attire as either proper or improper, based on government regulations. A dataset of 660 images was collected, equally divided between proper and improper attire. To build and validate the model, the data was divided into 20% testing (132 photos) and 80% training (528 images). The SVM classifier achieved an accuracy of 73%, demonstrating its effectiveness in recognizing dress code compliance. The study also compared SVM with other classification techniques, highlighting is robustness and reliability for this application. The findings suggest that machine learning can serve as a decision support tool for government offices, automating compliance monitoring and reducing manual enforcement efforts. Future work may involve integrating deep learning models, expanding the dataset, and implementing real-time classification systems. This research contributes to the intersection of technology, cultural norms and professional regulations, providing insights into how technology enhance policy enforcement in public service environments.