Automated Fixed Asset Management System with Predictive Analytics

Abstract

This study presents the design and development of an Automated Fixed Asset Management System with Predictive Analytics, which integrates QR code technology and machine learning to enhance asset tracking processes in organizations. The system aims to address common inefficiencies associated with traditional manual methods by automating asset registration, retrieval, and depreciation monitoring. Through QR codes, assets can be easily identified and tracked, reducing human error and improving inventory accuracy. The integration of predictive analytics, namely linear regression and random forest algorithms, enables the system to forecast lapsing schedules and asset lifecycles, supporting proactive decision-making and efficient resource allocation. Developed on the PHP Laravel framework, the system ensures secure user access, real-time synchronization, and regular data backups. It operates in both online and offline environments, making it adaptable to organizations with limited or inconsistent connectivity. A case implementation at Yusay Credit & Finance Corporation demonstrates the system’s capability to improve operational efficiency, reduce maintenance costs, and support scalable growth. This work contributes a robust and flexible solution for digital asset management tailored to the needs of mid-sized enterprises, particularly in developing regions where technology adoption is rapidly advancing.