<![CDATA[A laptop is a portable computing device that is widely relied upon because of the mobility it offers, particularly for users who spend much of their time outside a fixed office. Frequent and intensive use, however, raises the risk of damage to both hardware and supporting components. At present, the diagnosis of laptop damage is still largely performed manually by technicians based on experience, a practice that is prone to misdiagnosis and tends to take a relatively long time. This research therefore aims to implement the C4.5 Decision Tree algorithm to analyze and diagnose laptop damage based on the symptoms that appear. The data used in this study consist of laptop service history records comprising several damage-symptom attributes, such as whether the laptop powers on, the condition of the screen display, the charging indicator, fan noise, and overheating condition. The C4.5 algorithm was used to build a decision tree by calculating entropy, information gain, and gain ratio values in order to determine the best attribute for the classification process. Calculations on the training data produced a total entropy value of 2.75, with Attribute 1 (the laptop turning off immediately when the charger is unplugged) and Attribute 3 (a BSOD with a MEMORY_MANAGEMENT code) sharing the highest information gain of 0.81125, making either eligible to serve as the root node; this research adopted Attribute 1 as the root. The resulting decision tree was then implemented into a web-based diagnostic application built with PHP and MySQL, and black box testing confirmed that the login, data management, C4.5 modeling, and damage-classification features all functioned as expected. The system is expected to help technicians and customers at Mitra Kreasi Computer Medan obtain faster, more structured, and more objective damage diagnoses.]]>
Copyrights © 2026
