Prayoga, Rahmad (2025) Klasifikasi Anak Berhadapan Dengan Hukum Menggunakan Algoritma K-NN ( studi Kasus : Sentra Abiseka Kota Pekanbaru. Other thesis, Universitas Islam Riau.

Text skripsi_203510514_watermark.pdf - Submitted Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Children in Conflict with the Law (CICL) represent a serious issue that requires timely and appropriate intervention. At Sentra Abiseka in Pekanbaru City, the classification process for CICL is still conducted manually, leading to delays in case handling and a lack of data-driven decision-making based on children's characteristics. This study aims to develop a web-based classification system to categorize CICL as either offenders or victims using the K-Nearest Neighbor (KNN) algorithm. The dataset used in this study was obtained from Sentra Abiseka and consists of 112 child records with 9 main attributes: gender, case type, age, last education level, family economic condition, parents' occupation, number of family members, history of substance abuse, and peer relationships. The research stages include data preprocessing, handling class imbalance using SMOTE, model training and testing using k-fold cross-validation, and evaluation based on accuracy. The results indicate that the K-NN algorithm can accurately classify CICL cases and support stakeholders in making more efficient and structured decisions.

Actions (login required)

View Item