IMPROVED FARM MANAGEMENT SYSTEM FOR ANIMAL/LIVESTOCK PRODUCTION
Abstract
The escalating global demand for animal products necessitates innovative solutions to enhance livestock production efficiency and sustainability. This study developed an Improved Farm Management System, a software-based platform leveraging data analytics to optimize livestock health, nutrition, and breeding. Utilizing a synthetic Dairy Cow Health and Production Dataset with 1000 records, the system employs Random Forest models to predict cow health status and milk yield, achieving robust performance with 87% accuracy for classification and an RMSE of 2.05 liters for regression. Implemented as a Flask-based web application, the system supports local deployment with SQLite and offline functionality, ensuring accessibility for smallholder farmers, while offering scalability through PostgreSQL and cloud integration. The CRISP-DM methodology guided the development, encompassing data preprocessing, model training, and deployment. Results demonstrate the system’s potential to address inefficiencies in traditional livestock management, with implications for food security and sustainable agriculture. Future work includes integrating real-world datasets and IoT for automated data collection.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.