Increasing the Prediction Power of Moodle Machine Learning Models with Self-defined Indicators

Abstract

Starting with version 3.4 of Moodle, it has been possible to build educational ML models using predefined indicators in the Analytics API. Thesemodels can be used primarily to identify students at risk of failure. Our researchshows that the goodness and predictability of models built using predefined coreindicators in the API lags far behind the generally acceptable level. Moodle is anopen-source system, which on the one hand allows the analysis of algorithms,and on the other hand its modification and further development. Utilizing theopenness of the system, we examined the calculation algorithm of the core indicators,and then, based on the experience, we built new models with our ownindicators. Our results show that the goodness of models built on a given coursecan be significantly improved. In the article, we discuss the development processin detail and present the results achieved