College Student Retention Risk Analysis From Educational Database using Multi-Task Multi-Modal Neural Fusion

TL;DR

This paper introduces a novel multimodal neural network that combines structured and unstructured student data to accurately predict multiple college student retention risks, demonstrating promising results on a large educational dataset.

Contribution

The paper presents a new multimodal neural fusion model with multi-task learning for comprehensive student retention risk prediction, integrating text and structured data.

Findings

Achieved improved prediction accuracy over state-of-the-art models.

Effectively fused textual and structured data for richer student representations.

Evaluated model fairness considering biases in educational data.

Abstract

We develop a Multimodal Spatiotemporal Neural Fusion network for Multi-Task Learning (MSNF-MTCL) to predict 5 important students' retention risks: future dropout, next semester dropout, type of dropout, duration of dropout and cause of dropout. First, we develop a general purpose multi-modal neural fusion network model MSNF for learning students' academic information representation by fusing spatial and temporal unstructured advising notes with spatiotemporal structured data. MSNF combines a Bidirectional Encoder Representations from Transformers (BERT)-based document embedding framework to represent each advising note, Long-Short Term Memory (LSTM) network to model temporal advising note embeddings, LSTM network to model students' temporal performance variables and students' static demographics altogether. The final fused representation from MSNF has been utilized on a Multi-Task Cascade Learning (MTCL) model towards building MSNF-MTCL for predicting 5 student retention risks. We evaluate MSNFMTCL on a large educational database consists of 36,445 college students over 18 years period of time that provides promising performances comparing with the nearest state-of-art models. Additionally, we test the fairness of such model given the existence of biases.