Unplanned downtime in offshore oilfield infrastructure, particularly in subsea systems and Floating Production Storage and Offloading (FPSO) units, poses significant operational, safety, and economic challenges. These complex systems operate in remote and harsh environments, where failure of critical components can lead to prolonged outages, costly repairs, and production losses. Traditional reactive or time-based maintenance strategies are often inadequate for preventing unexpected equipment failures in such settings. To address this gap, this study proposes a predictive analytics model designed to forecast potential failures and minimize unplanned downtime in subsea and FPSO infrastructure. The model integrates real-time and historical operational data—such as pressure, temperature, vibration, and flow rate—using advanced machine learning techniques including anomaly detection and time-series forecasting. A layered architecture is developed, comprising data acquisition, preprocessing, predictive modeling, and decision-support components. Key performance indicators (KPIs) such as downtime probability, equipment health scores, and maintenance urgency indices are derived to guide operational decisions. The predictive model is validated through a case study involving a representative offshore production system, demonstrating its ability to detect early signs of equipment degradation and recommend timely interventions. The results indicate significant potential for improving maintenance efficiency, enhancing asset reliability, and reducing production losses due to unplanned events. In addition to technical design, the study addresses practical implementation considerations including data integration challenges, model training, and real-time alert mechanisms. The model also emphasizes scalability and adaptability across different offshore asset configurations. This research highlights the strategic importance of predictive analytics in transitioning offshore oil and gas operations from reactive to proactive asset management. It contributes to advancing digital transformation in offshore production systems, promoting safer, more resilient, and cost-effective operations in high-risk deepwater environments.