Publication: Predictive analytics for rice production and yields through machine learning
No Thumbnail Available
Date
2024-12
Journal Title
Journal ISSN
Volume Title
Publisher
Don Mariano Marcos Memorial State University – Mid La Union Campus
Abstract
This study aimed to predict rice production and yields in the Province of La Union using a dataset collected from Department of Agriculture Regional Office I. The research employed the CRISP-DM methodology, utilizing machine learning algorithms, focusing on the Random Forest model due to itshigh accuracy and robustness. The dataset included key variablessuch as year, land area, types of seeds, water source, seasons, and municipalities, which were analyzed and processed to train the model. The structured approach of CRISP-DM ensured a comprehensive analysis through its phases: business
understanding, data understanding, data preparation, modeling, evaluation, and deployment. Preliminary results demonstrated that the Random Forest model achieved excellent accuracy in predicting rice yields, providing valuable insights for agricultural stakeholders. These insights assisted in strategic agricultural planning, resource allocation, and sustainable farming practices, emphasizing the potential of machine learning in enhancing food security.
Description
Keywords
Citation
Ramos, M. A. V., Estacio, J. D. B., Indong, R. I. C., & Partible, A. C. (2024) [Unpublished Undergraduate Feasibility Study]. Don Mariano Marcos Memorial State University – Mid La Union Campus. Lakasa ti Sirib, DMMMMSU Institutional Repository.