Von P. Gabayan^1,, Lemuel C. Sanchez¹, Sherilyn P. Tobias¹, Michael John R. Robles¹, Carmelo Alejo D. Bisquera¹

This study, titled Unveiling Patterns and Predictions: A Systematic Review on Predictive Classification and Trend Forecasting in Faculty Performance Evaluation in Philippine Higher Education, examines how predictive analytics and machine learning models are revolutionizing faculty evaluation systems. Through a systematic literature review using a Narratological Approach, several studies from 2019 to 2025 were analyzed to trace the evolution from traditional descriptive evaluation toward data-driven and predictive methodologies. The findings reveal that models such as Decision Trees, Random Forest, Naïve Bayes, ARIMA, and LSTM effectively classify performance outcomes and forecast developmental trends. Key determinants influencing predictive accuracy include pedagogical competence, research productivity, ICT integration, workload balance, and professional engagement. Forecasting models further enable institutions to anticipate faculty growth trajectories and design timely interventions. However, challenges such as fragmented data systems, limited analytics literacy, and ethical concerns constrain implementation within Philippine higher education. The study concludes that integrating predictive classification and trend forecasting can transform evaluation into a proactive, evidence-based process that fosters continuous improvement. Further, Unveiling Patterns and Predictions represents a paradigm shift—where faculty performance evaluation evolves from static assessment into a dynamic mechanism for institutional growth, innovation, and excellence in the digital age.

Predictive Analytics, Faculty Evaluation, Trend Forecasting