The power of noise and the art of prediction

Abstract

Data analysis usually aims to identify a particular signal, such as an intervention effect. Conventional analyses often assume a specific data generation process, which suggests a theoretical model that best fits the data. Machine learning techniques do not make such an assumption. In fact, they encourage multiple models to compete on the same data. Applying logistic regression and machine learning algorithms to real and simulated datasets with different features of noise and signal, we demonstrate that no single model dominates others under all circumstances. By showing when different models shine or struggle, we argue it is both possible and important to conduct comparative analyses.

Decision Trees for Evaluation of Mathematical Competencies in the Higher Education: A Case Study

“…Some specifics for applying machine-learning approaches in the field of education are examined [28] for the cases of K-Nearest Neighbors (K-NN), logistic regression, and random forest. An overview of a large number of publications applying data mining is summarized and discussed in review papers [29][30][31].…”