Paper Info
Title
Prediction of Learners' Academic Performance Using Factorization Machine and Decision Tree
Abstract
The capacity to predict learner's academic performance accurately is critical for online learning platforms. Based on obtained predictions, platform managers can formulate appropriate policies for different students to improve the online learning experience for all online learners. The real-world data from Peking University's open research data platform contained e-learning data such as e-learning behaviors of students, are used in this study. According to the dataset, we apply four decision tree methods and factorization machine (FM) method to create prediction models. The experimental results show that students are categorized into two types of learning, namely interactive learning, and autonomous learning. Qualified students and outstanding students have different performances in the two types of learning. Furthermore, the experiments revealed that considering the interaction between e-learning behaviors can effectively improve the predictive ability of the model. We believe that our research results can provide effective support for further development in e-learning and our subsequent research work.
Year
DOI
Venue
2019
10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00024
2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
Keywords
Field
DocType
e-learning, e-learning behavior, decision classifycation tree, FM
Open research,Decision tree,Interactive Learning,Computer science,Artificial intelligence,Factorization,Predictive modelling,Statistical classification,Entropy (information theory),Machine learning,Autonomous learning
Conference
ISBN
Citations 
PageRank 
978-1-7281-2981-5
0
0.34
References 
Authors
14
2
Name
Order
Citations
PageRank
Junjie Hou100.34
Yiping Wen2258.59