Journal article
Towards Interpretable Automated Machine Learning for STEM Career Prediction
Journal of educational data mining, Vol.12(2), pp.19-32
2020
DOI: 10.5281/zenodo.4008073
Abstract
In this paper, we describe our solution to predict student STEM career choices during the 2017 ASSISTments Datamining Competition. We built a machine learning system that automatically reformats the data set, generates new features and prunes redundant ones, and performs model and feature selection. We designed the system to automatically find a model that optimizes prediction performance, yet the final model is a simple logistic regression that allows researchers to discover important features and study their effects on STEM career choices. We also compared our method to other methods, which revealed that the key to good prediction is proper feature enrichment in the beginning stage of the data analysis, while feature selection in a later stage allows a simpler final model.
Details
- Title: Subtitle
- Towards Interpretable Automated Machine Learning for STEM Career Prediction
- Creators
- Ruitao Liu - NebulAI EducationAixin Tan - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Journal of educational data mining, Vol.12(2), pp.19-32
- DOI
- 10.5281/zenodo.4008073
- ISSN
- 2157-2100
- eISSN
- 2157-2100
- Publisher
- International Educational Data Mining
- Number of pages
- 14
- Language
- English
- Date published
- 2020
- Description audience
- Middle Schools; Junior High Schools; Secondary Education
- Academic Unit
- Statistics and Actuarial Science
- Record Identifier
- 9984257743702771
Metrics
7 Record Views