<![CDATA[This study investigates the impact of programming paradigm selection on the efficiency and sustainability of machine learning (ML) pipeline design. A case study was conducted using an agricultural IoT dataset for crop yield prediction, where four paradigms imperative, functional, object-oriented (OOP), and declarative were implemented to construct modular, maintainable, and reproducible pipelines. Each paradigm was evaluated through five key metrics: development time, debugging time, modularity, reproducibility, and maintainability. Experimental data were analyzed using descriptive statistics and visualized with boxplots and radar charts to identify performance differences. The results demonstrate that the functional paradigm achieved superior performance in data preprocessing with high reproducibility (95%), OOP produced the highest modularity (5.0/5), while the declarative paradigm exhibited the best reproducibility (98%) and deployment efficiency. In contrast, the imperative paradigm enabled faster prototyping but lacked long-term stability. Integrating paradigms in a multi-paradigm design reduced development time by 30.3%, debugging effort by 41.2%, and improved modularity and reproducibility by 41.6% and 21%, respectively. These findings highlight that no single paradigm is universally optimal; instead, a multi-paradigm approach provides a more efficient, maintainable, and production-ready ML pipeline framework adaptable to industrial-scale implementations.]]>
Copyrights © 2026
