ENHANCED EXAMINATION MALPRACTICE DETECTION MODEL USING XGBOOST AND DECISION TREE TECHNIQUES

Abstract

The research examines the Enhancement of Examination Malpractice Detection System Using XGBoost
Machine and Decision Tree Algorithm. A Gradient boosting machine learning algorithm and a decision
tree algorithm using the captured student fingerprint are used to track student’s bio data during
examination so as to detect examination malpractices. Findings revealed that machine-learning
application improved the efficiency and performance of Examination malpractice detection system
through neural analysis, interpretation and interface to the existing database management system
which contains the sample of students’ handwriting. The software development methodology adopted
for the development of the system is Structured System Analysis and Design Methodology (SSADM).
The programming language used is java, php and the database used is MySql. The designed system
was implemented as the Enhanced Examination Malpractice Detection System Using XGBoost
Machine and Decision Tree Algorithm which was tested and found successful.