In the heart of North Sumatra, where the demand for pineapples is on the rise, a novel approach to boosting productivity is emerging from an unlikely source: machine learning. Researchers at Universitas Islam Negeri Sumatera Utara have turned to the Naïve Bayes algorithm, a lightweight yet powerful tool, to classify pineapple productivity based on agronomic characteristics. This study, led by Suendri Suendri, offers a practical solution to a pressing agricultural challenge, demonstrating that advanced technology can be both accessible and effective.
The study, published in *Intensif: Jurnal Ilmiah Penelitian Teknologi dan Penerapan Sistem Informasi* (translated to *Intensif: Scientific Journal of Research on Technology and Application of Information Systems*), addresses a critical gap in the field. While machine learning has been widely applied in agriculture, most prior studies on pineapple have focused on fruit quality assessment or employed complex models that are less interpretable. Suendri’s research, however, highlights the potential of the Naïve Bayes algorithm, which is known for its simplicity and efficiency.
“Our goal was to evaluate the effectiveness of the Naïve Bayes algorithm in classifying pineapple productivity,” Suendri explained. “We wanted to provide a practical, interpretable model that could be easily implemented by farmers and agricultural extension services.”
The study utilized secondary data from the Labuhan Batu Agricultural Extension Center, consisting of 52 records with seven agronomic parameters. The dataset was divided into training and testing samples, and the Naïve Bayes model was implemented using RapidMiner 7.1. The results were impressive, with the model achieving an accuracy of 86.67%. This high accuracy demonstrates the model’s suitability for agricultural classification tasks, even with limited data.
The implications of this research are significant for the agricultural sector, particularly in regions like North Sumatra where pineapple is a major commodity. By providing a tool that can accurately classify pineapple productivity, farmers can make more informed decisions about crop management, ultimately leading to increased yields and economic benefits.
“This study highlights the novelty and practicality of applying Naïve Bayes for pineapple productivity classification,” Suendri noted. “It offers an interpretable and computationally efficient alternative to more complex models.”
Looking ahead, the research team plans to address the limitations of the small dataset by incorporating larger and more diverse samples. They also aim to explore hybrid or ensemble approaches to further enhance the model’s performance. These advancements could pave the way for more precise and efficient agricultural practices, supporting the broader goals of precision agriculture.
As the demand for pineapples continues to grow, the need for innovative solutions to boost productivity becomes ever more pressing. Suendri’s research offers a promising step forward, demonstrating that machine learning can be a powerful ally in the quest for agricultural sustainability and profitability.