Student retention analysis
Gautam, Lok Mani (2024)
2024
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2024052214191
https://urn.fi/URN:NBN:fi:amk-2024052214191
Tiivistelmä
For colleges and universities, student attrition comes with substantial finan-cial and reputational cost. This study aimed to analyse the different factors contributing for the student dropout and to develop a predictive model to identify students at risk of dropping out. Dataset encompassing 4424 stu-dents’ records were analysed, including demographic factors, economic fac-tors, Academic performance, social and special needs, and macro-economic factors.
Along with feature selection techniques, various machine learning algo-rithms were employed, among which Random Forest model achieved the highest accuracy (76%). Academic performance, Demographic factors and economic factors emerged as the key predictive factors for student success. These findings help to identify high-risk students and provide support and develop polices to foster a conductive learning environment.
This thesis utilizes exploratory data analysis (EDA) and machine learning techniques to forecast and explain the factors contributing for student drop-out.
Along with feature selection techniques, various machine learning algo-rithms were employed, among which Random Forest model achieved the highest accuracy (76%). Academic performance, Demographic factors and economic factors emerged as the key predictive factors for student success. These findings help to identify high-risk students and provide support and develop polices to foster a conductive learning environment.
This thesis utilizes exploratory data analysis (EDA) and machine learning techniques to forecast and explain the factors contributing for student drop-out.