Aggregating Time Series and Tabular Data in Deep Learning Model for University Students' GPA Prediction

被引：8

作者：

Prabowo, Harjanto ^{[1
]}

Hidayat, Alam Ahmad ^{[2
]}

Cenggoro, Tjeng Wawan ^{[2
,3
]}

Rahutomo, Reza ^{[2
]}

Purwandari, Kartika ^{[2
]}

Pardamean, Bens ^{[2
,4
]}

机构：

[1] Bina Nusantara Univ, Management Dept, BINUS Business Sch Undergrad Program, Jakarta 11480, Indonesia

[2] Bina Nusantara Univ, Bioinformat & Data Sci Res Ctr, Jakarta 11480, Indonesia

[3] Bina Nusantara Univ, Sch Comp Sci, Comp Sci Dept, Jakarta 11480, Indonesia

[4] Bina Nusantara Univ, BINUS Grad Program, Comp Sci Dept, Master Comp Sci Program, Jakarta 11480, Indonesia

来源：

IEEE ACCESS | 2021年 / 9卷

关键词：

Educational data mining; deep learning; GPA prediction; time-series data; tabular data; PERFORMANCE;

D O I：

10.1109/ACCESS.2021.3088152

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Current approaches of university students' Grade Point Average (GPA) prediction rely on the use of tabular data as input. Intuitively, adding historical GPA data can help to improve the performance of a GPA prediction model. In this study, we present a dual-input deep learning model that is able to simultaneously process time-series and tabular data for predicting student GPA. Our proposed model achieved the best performance among all tested models with 0.4142 MSE (Mean Squared Error) and 0.418 MAE (Mean Absolute Error) for GPA with a 4.0 scale. It also has the best R-2-score of 0.4879, which means it explains the true distribution of students' GPA better than other models.

引用

页码：87370 / 87377

页数：8

共 50 条

[41] Special issue on deep learning for time series data
Ma, Ruizhe
Angryk, Rafal
Scherer, Rafal
[J]. NEURAL COMPUTING & APPLICATIONS, 2022, 34 (16): : 13147 - 13148
[42] Deep compartment models: A deep learning approach for the reliable prediction of time-series data in pharmacokinetic modeling
Janssen, Alexander
Leebeek, Frank W. G.
Cnossen, Marjon H.
Mathot, Ron A. A.
[J]. CPT-PHARMACOMETRICS & SYSTEMS PHARMACOLOGY, 2022, 11 (07): : 934 - 945
[43] Special issue on deep learning for time series data
Ruizhe Ma
Rafal Angryk
Rafal Scherer
[J]. Neural Computing and Applications, 2022, 34 : 13147 - 13148
[44] Dense Representation Learning and Retrieval for Tabular Data Prediction
Zheng, Lei
Li, Ning
Chen, Xianyu
Gan, Quan
Zhang, Weinan
[J]. PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 3559 - 3569
[45] Ice prediction for wind turbine rotor blades with time series data and a deep learning approach
Kreutz, Markus
Alla, Abderrahim Ait
Luetjen, Michael
Ohlendorf, Jan-Hendrik
Freitag, Michael
Thoben, Klaus-Dieter
Zimnol, Florian
Greulich, Andreas
[J]. COLD REGIONS SCIENCE AND TECHNOLOGY, 2023, 206
[46] Time Series Prediction Using Deep Learning Methods in Healthcare
Morid, Mohammad Amin
Sheng, Olivia R. Liu
Dunbar, Joseph
[J]. ACM TRANSACTIONS ON MANAGEMENT INFORMATION SYSTEMS, 2023, 14 (01)
[47] Retail Time Series Prediction Based on EMD and Deep Learning
Mou, Shucheng
Ji, Yang
Tian, Chujie
[J]. PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON NETWORK INFRASTRUCTURE AND DIGITAL CONTENT (IEEE IC-NIDC), 2018, : 425 - 430
[48] Computer Model Calibration with Time Series Data Using Deep Learning and Quantile Regression
Bhatnagar, Saumya
Chang, Won
Kim, Seonjin
Wang, Jiali
[J]. SIAM-ASA JOURNAL ON UNCERTAINTY QUANTIFICATION, 2022, 10 (01): : 1 - 26
[49] Urban and regional distinctions for aggregating time series data
Cutler, Harvey
England, Scott
Weiler, Stephan
[J]. PAPERS IN REGIONAL SCIENCE, 2007, 86 (04) : 575 - 595
[50] TableNN: Deep Learning Framework for Learning Domain Specific Tabular Data
Sankhe, Pranav
Khabiri, Elham
Agrawal, Bhavna
Li, Yingjie
[J]. Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021, 2021, : 4097 - 4102

← 1 2 3 4 5 →