AI-Assisted Revenue Leakage Detection in Turnover Rent Operations across Multi-Mall Retail Property Portfolios: A Predictive Analytics Framework for Revenue Assurance and Intelligent Retail Asset Management

The rapid expansion of large-scale retail property portfolios has increased the complexity of revenue management, particularly in turnover rent operations where rental income depends on accurate tenant sales reporting and contractual compliance. Traditional revenue assurance approaches rely primarily on periodic audits, manual verification, and tenant-declared sales information, which may result in delayed identification of revenue leakage caused by inaccurate reporting, operational inconsistencies, and fragmented data sources. This research proposes an Artificial Intelligence (AI)-assisted framework for detecting and preventing revenue leakage in multi-mall retail environments through predictive analytics, machine learning-based anomaly detection, and intelligent contract analysis. The proposed framework integrates multiple data streams, including tenant sales records, point-of-sale transactions, lease agreements, payment histories, and operational performance indicators to identify abnormal revenue patterns and estimate potential leakage risks. The study develops an AI-driven revenue assurance model capable of continuous monitoring, risk classification, and proactive decision support for retail asset managers. The research contributes to the digital transformation of retail real estate management by demonstrating how AI technologies can improve transparency, financial control, and operational efficiency across complex mall ecosystems. The proposed approach provides a scalable solution for property operators seeking to enhance revenue protection and establish intelligent, data-driven turnover rent management practices.