A Statistical Framework for Predictive Model Evaluation in MOOCs. Gardner, J. & Brooks, C. In Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale, of L@S '17, pages 269–272, Cambridge, MA, USA, April, 2017. Association for Computing Machinery.
A Statistical Framework for Predictive Model Evaluation in MOOCs [link]Paper  doi  abstract   bibtex   
Feature extraction and model selection are two essential processes when building predictive models of student success. In this work we describe and demonstrate a statistical approach to both tasks, comparing five modeling techniques (a lasso penalized logistic regression model, naïve Bayes, random forest, SVM, and classification tree) across three sets of features (week-only, summed, and appended). We conduct this comparison on a dataset compiled from 30 total offerings of five different MOOCs run on the Coursera platform. Through the use of the Friedman test with a corresponding post-hoc Nemenyi test, we present comparative performance results for several classifiers across the three different feature extraction methods, demonstrating a rigorous inferential process intended to guide future analyses of student success systems.
@inproceedings{gardner_statistical_2017,
	address = {Cambridge, MA, USA},
	series = {L@{S} '17},
	title = {A {Statistical} {Framework} for {Predictive} {Model} {Evaluation} in {MOOCs}},
	isbn = {978-1-4503-4450-0},
	url = {http://doi.org/10.1145/3051457.3054002},
	doi = {10.1145/3051457.3054002},
	abstract = {Feature extraction and model selection are two essential processes when building predictive models of student success. In this work we describe and demonstrate a statistical approach to both tasks, comparing five modeling techniques (a lasso penalized logistic regression model, naïve Bayes, random forest, SVM, and classification tree) across three sets of features (week-only, summed, and appended). We conduct this comparison on a dataset compiled from 30 total offerings of five different MOOCs run on the Coursera platform. Through the use of the Friedman test with a corresponding post-hoc Nemenyi test, we present comparative performance results for several classifiers across the three different feature extraction methods, demonstrating a rigorous inferential process intended to guide future analyses of student success systems.},
	urldate = {2020-09-23},
	booktitle = {Proceedings of the {Fourth} (2017) {ACM} {Conference} on {Learning} @ {Scale}},
	publisher = {Association for Computing Machinery},
	author = {Gardner, Josh and Brooks, Christopher},
	month = apr,
	year = {2017},
	keywords = {machine learning, model evaluation, mooc, predictive modeling},
	pages = {269--272}
}

Downloads: 0