How can data science and advanced analytics be effectively applied to improve production performance and well decision making across complex upstream operations? This session presents practical applications of machine learning and advanced analytics supporting both well engineering and production optimization workflows. Through real field case studies, the papers demonstrate how data driven methods are being used to forecast operational parameters, estimate remaining useful life, enhance artificial lift performance, optimize production scheduling, and prioritize well interventions to maximize asset value. Topics covered include forecasting models for offshore wells, automated updating and calibration of nodal analysis models, portfolio level optimization for intervention and IOR strategy prioritization, AI driven production scheduling to improve net present value, smart dynagraph interpretation using machine learning, and integrated early warning systems for formation damage and production risk detection. Rather than focusing on theoretical models, this session emphasizes practical implementation, scalability, and decision support. Attendees will gain insight into how advanced analytics can bridge the gap between subsurface, wells, and production operations, enabling engineers to shift from reactive troubleshooting to proactive, data driven performance management.