CC BY 4.0Torres, Doreen A.Rivera, Mark Lydrion M.Apilado, Bennidict M.Dantay, Leiann Drew D.Marquez, Mark EmersonReolegio, Jan Rielan H.2026-03-132026-03-132024-12Rivera, M. L. M., Apilado, B. M., Dantay, L. D. D., Marquez, M. E., & Reolegio, J. R. H. (2024). Feathered forecast: using analytics to predict egg yields. [Unpublished Undergraduate Thesis]. Don Mariano Marcos Memorial State University - Mid La Union Campus, City of San Fernando, La Union. Lakasa ti Sirib, DMMMSU Institutional Repository.https://lakasa.dmmmsu.edu.ph/handle/123456789/1191Full textThis study tackled the factors of poultry egg production and developed a predictive model and system prototype. Key factors included chicken age and seasonal patterns or variation. Using the CRISP-DM methodology, data sets were gathered, cleaned, and trained using different models. Random Forest, Support Vector Machines, and Neural Networks were utilized to predict egg yields. Among the four models, Random Forest had the best prediction and performance based on the different metrics. The researchers also developed a web-based system prototype that integrated the prediction result using Random Forest. The system can enhance resource planning and aid in better decision-making. The system had a usability score of 83.20 on the SUS, which makes it a valuable combination of technology and data insights to enhance poultry farming productivity.xi, 72 p. : ill. (col.).enFORESTRY, AGRICULTURAL SCIENCES and LANDSCAPE PLANNING::Area economics::Agricultural economicsAnalyticsAgricultural scienceMachine learningAgriculture--Data processing--Management applicationsOperations management--Production forecastingAgricultural forecastingMachine learningThesis