Effectively managing oil rim reservoirs poses significant challenges due to uncertainties in predicting oil rim movements. This leads to production losses, high gas-to-oil ratios (GOR), increased water cut, and the risk of losing the oil rim. To address these issues, a proof of concept for an early warning system was developed, utilizing innovative data analytics techniques and leveraging well data, such as pressure and temperature measurements, to detect changes in water cut as an indicator of oil rim movement. The workflow involves data extraction, pre-processing, regime detection, trend analysis, and exception-based surveillance with alerts. A selected oil-producing well with ample flow line pressure, temperature, and well test data was used to test the workflow. Pipesim modeling indicated a clear correlation between temperature and water cut, validated through sensitivity analysis at different GOR levels. The technology provides an integrated workflow covering data management, analytics, an event detection alert algorithm, and a visualization dashboard. It is not intended to replace existing oil rim management tools but serves as an additional decision support tool when reliable models are unavailable. The early warning system presented in this paper addresses the limitations of current methods by offering a proactive approach to detect fluid movements and mitigate production losses. By integrating novel data analytics techniques and utilizing readily available well data, operators can make informed decisions and take timely actions, improving the efficiency and effectiveness of oil rim management in petroleum operations. This technology serves as a valuable decision support tool in the absence of reliable models, ultimately enhancing the overall performance of oil rim management strategies.