Claim Missing Document
Check
Articles

Found 1 Documents
Search

A Decision Support System for the Selection and Distribution of Superior Durian Seedlings to the Community Using the Decision Tree Method Danisuwara, Ardiya Kansya; Manurung, Hotler; Simanjuntak, Magdalena
Pascal: Journal of Computer Science and Informatics Vol. 2 No. 02 (2025): Pascal: Journal of Computer Science and Informatics
Publisher : Devitara Innovations

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The durian fruit is an agricultural commodity with high economic value and strong demand both domestically and internationally. However, the success rate of durian cultivation in Indonesia remains relatively low, at approximately 30.3%. This is partly due to the limited experience of farmers in managing durian plantations and the absence of an objective system for selecting eligible recipients of superior seedlings. Inaccurate selection of seedling recipients can lead to low productivity, suboptimal fruit quality, and an imbalance between market supply and demand. To address these issues, this study proposes the development of a Decision Support System (DSS) for the selection of superior durian seedling recipients using the Decision Tree algorithm. The study identifies several factors influencing eligibility, including age, land area, land ownership, farming experience, socioeconomic status, number of plants, water availability, membership in farmer groups, regional location, and education level. Data from 300 respondents were collected and processed through several preprocessing stages, including categorical data encoding, numerical data binning, normalization, and the division of training and testing datasets. The Decision Tree model was developed using the Scikit-learn library in the Python programming language, with the Gini index as the splitting criterion. The experimental results indicate that the model achieved an accuracy of 85%, a precision of 90%, and a recall of 95% for the "Eligible" class, demonstrating the system’s effectiveness in accurately identifying qualified recipients. The system was implemented as a GUI-based desktop application using Tkinter, equipped with features for data input, eligibility prediction, recipient data management, and statistical visualization. The implementation of this system is expected to enhance objectivity, efficiency, and accountability in the distribution of superior durian seedlings, thereby contributing to increased productivity among durian farmers and promoting better market equilibrium.