Early student dropout detection in Indian secondary education with special reference to selected districts in Tamil Nadu: a machine learning-based survival analysis approach

Raghul Gandhi Venkatesan () and Bagavandas Mappillairaju ()
Additional contact information
Raghul Gandhi Venkatesan: SRM Institute of Science & Technology
Bagavandas Mappillairaju: SRM Institute of Science & Technology

Journal of Computational Social Science, 2024, vol. 7, issue 3, No 4, 2309-2331

Abstract: Abstract Education is crucial for individual growth and national development. India, with its ambitious School Education Vision 2030, aims to overcome persistent challenges in achieving universal education. This study examines the complex issue of student dropout, specifically focusing on the secondary level in Tamil Nadu, by analyzing the demographic profiles of 846 students. Machine Learning classification approaches such as Logistic Regression, Support Vector Machine, Multi-Layer Perceptron, and Random Forest demonstrate impressive performances, with Random Forest standing out as a powerful tool for accurate prediction. In dropout prediction, survival analysis approaches, specifically the Random Survival Forest (RSF) model, outperform the Weibull model. Through variable importance analysis, age and attendance are found to be significant factors, emphasizing their critical role in predicting dropout events. This study pioneers the integration of survival analysis and machine learning-based classification in the Indian educational context, contributing to the improvement of dropout prediction models. The combined approach enhances the accuracy of dropout prediction and temporal understanding. Despite its cohort-specific focus, the study provides valuable insights for future research and interventions, supporting inclusive education in India by integrating essential characteristics in predictive models.

Keywords: Dropout; Determinants; Machine learning; Survival analysis; Secondary education (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42001-024-00309-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jcsosc:v:7:y:2024:i:3:d:10.1007_s42001-024-00309-z

Ordering information: This journal article can be ordered from
http://www.springer. ... iences/journal/42001

DOI: 10.1007/s42001-024-00309-z

Access Statistics for this article

Journal of Computational Social Science is currently edited by Takashi Kamihigashi

More articles in Journal of Computational Social Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().