A Novel Framework for E-Waste Inventory Based on IoT, Cloud Computing, and Machine Learning Technologies: The Case of Saudi Arabia

Electronic waste is rising rapidly worldwide, and Saudi Arabia currently produces the largest share within the Arab region. Existing studies focus on isolated technologies or regional snapshots; none combine cloud computing, Internet‑of‑Things (IoT) sensing, and machine‑learning prediction in a single, traceable national inventory. To address this gap, this paper presents a hybrid cloud–IoT framework with an integrated machine‑learning model for forecasting e‑waste flows in Saudi Arabia. The architecture links stakeholders to scalable cloud services and IoT‑equipped collection bins that assign unique identifiers and transmit real‑time data, while the predictive model learns from historical records to estimate future volumes. Validation will draw on a secondary e‑waste dataset, a structured stakeholder survey analyzed with standard statistical procedures, and simulation studies that test data movement from edge devices to the cloud under variable loads. Expected results include higher inventory accuracy, faster collection cycles, improved transparency for regulators, and closer alignment with Vision 2030 sustainability targets. Survey findings and model performance metrics will be compared with current collection practices to quantify gains in efficiency and resource recovery. These insights will provide evidence for policymakers and industrial partners planning large‑scale deployment and will lay the groundwork for wider adoption of distributed digital solutions in the circular economy.