Synthetic Embedding-based Data Generation Methods for Student Performance

TL;DR

This paper proposes a novel synthetic embedding-based data generation framework (SEDG) to address class imbalance in student performance datasets, improving predictive accuracy of machine learning models.

Contribution

The paper introduces SEDG, a search-based method for generating synthetic samples using embeddings, which outperforms traditional re-sampling techniques in class imbalance scenarios.

Findings

SEDG outperforms traditional re-sampling methods for deep neural networks.

SEDG performs competitively on standard classifiers.

Improves learning on imbalanced student performance datasets.

Abstract

Given the inherent class imbalance issue within student performance datasets, samples belonging to the edges of the target class distribution pose a challenge for predictive machine learning algorithms to learn. In this paper, we introduce a general framework for synthetic embedding-based data generation (SEDG), a search-based approach to generate new synthetic samples using embeddings to correct the detriment effects of class imbalances optimally. We compare the SEDG framework to past synthetic data generation methods, including deep generative models, and traditional sampling methods. In our results, we find SEDG to outperform the traditional re-sampling methods for deep neural networks and perform competitively for common machine learning classifiers on the student performance task in several standard performance metrics.