Filters








27,542 Hits in 5.1 sec

Cumulative Knowledge-based Regression Models for Next-term Grade Prediction [chapter]

Sara Morsy, George Karypis
2017 Proceedings of the 2017 SIAM International Conference on Data Mining  
In this paper, we present a cumulative knowledge-based regression model with different courseknowledge spaces for the task of next-term grade prediction.  ...  Grade prediction for future courses not yet taken by students is important as it can help them and their advisers during the process of course selection as well as for designing personalized degree plans  ...  Conclusion In this paper, we modeled the next-term grade prediction problem in a traditional University setting as a Cumulative Knowledge-based Regression Model (CKRM) that accumulates the performance  ... 
doi:10.1137/1.9781611974973.62 dblp:conf/sdm/MorsyK17 fatcat:vvlblw4bmzggfgeqyp5sksiray

Predicting Student Performance Using Personalized Analytics

Asmaa Elbadrawy, Agoritsa Polyzou, Zhiyun Ren, Mackenzie Sweeney, George Karypis, Huzefa Rangwala
2016 Computer  
Personalized multiregression and matrix factorization approaches based on recommender systems, initially developed for e-commerce applications, accurately forecast students' grades in future courses as  ...  To help solve the ongoing problem of student retention, new expected performance-prediction techniques are needed to facilitate degree planning and determine who might be at risk of failing or dropping  ...  Next-term grade prediction In-class LMS assessment prediction We found that the features describing the student's cumulative GPA, cumulative grade, and viewing of course materials contributed most to  ... 
doi:10.1109/mc.2016.119 fatcat:hezysijl4neinnulswv2zmyfui

Next-Term Student Performance Prediction: A Recommender Systems Approach [article]

Mack Sweeney, Huzefa Rangwala, Jaime Lester, Aditya Johri
2016 arXiv   pre-print
To further this goal, we develop a system to predict students' grades in the courses they will enroll in during the next enrollment term by learning patterns from historical transcript data coupled with  ...  In our experiments, Factorization Machines (FM), Random Forests (RF), and the Personalized Multi-Linear Regression model achieve the lowest prediction error.  ...  The data for this study was made available through a collaborative effort spearheaded by Office of Institutional Research and Reporting and we would like to acknowledge Kris Smith, Kathryn Zora, Angela  ... 
arXiv:1604.01840v1 fatcat:cz27yygejjaxxgnioudgksdws4

ALE: Additive Latent Effect Models for Grade Prediction [chapter]

Zhiyun Ren, Xia Ning, Huzefa Rangwala
2018 Proceedings of the 2018 SIAM International Conference on Data Mining  
In this paper, we propose additive latent effect models that incorporate these factors to predict the student next-term grades.  ...  Grade prediction methods seek to estimate a grade that a student may achieve in a course that she may take in the future (e.g., next term).  ...  Acknowledgment Thanks to NSF Big Data Grant #1447489 and GMU IRR Staff for providing data.  ... 
doi:10.1137/1.9781611975321.54 dblp:conf/sdm/RenNR18 fatcat:ctctv4edazhmvkiklyxhimaouu

Sparse Neural Attentive Knowledge-based Models for Grade Prediction [article]

Sara Morsy, George Karypis
2019 arXiv   pre-print
One of the successful approaches for accurately predicting a student's grades in future courses is Cumulative Knowledge-based Regression Models (CKRM).  ...  In this paper, we propose a novel Neural Attentive Knowledge-based model (NAK) that learns the importance of each historical course in predicting the grade of a target course.  ...  Cumulative Knowledge-based Regression Models (CKRM) Morsy et al.  ... 
arXiv:1904.11858v1 fatcat:zzsagijo2jfatgdxqlk3dwhkte

Next-Term Student Performance Prediction: A Recommender Systems Approach

Mack Sweeney, Jaime Lester, Huzefa Rangwala, Aditya Johri
2016 Zenodo  
To further this goal, we develop a system to predict students' grades in the courses they will enroll in during the next enrollment term by learning patterns from historical transcript data coupled with  ...  In our experiments, Factorization Machines (FM), Random Forests (RF), and the Personalized Linear Multiple Regression model achieve the lowest prediction error.  ...  The data for this study was made available through a collaborative effort spearheaded by Office of Institutional Research and Reporting and we would like to acknowledge Kris Smith, Kathryn Zora, Angela  ... 
doi:10.5281/zenodo.3554603 fatcat:pumd64tp2nav5ohilnt2zal734

Why study time does not predict grade point average across college students: Implications of deliberate practice for academic performance

E. Ashby Plant, K. Anders Ericsson, Len Hill, Kia Asberg
2005 Contemporary Educational Psychology  
A model was proposed where performance in college, both cumulatively and for a current semester, was jointly determined by previous knowledge and skills as well as factors indicating quality (e.g., study  ...  The findings support the proposed model and indicate that the amount of study only emerged as a significant predictor of cumulative GPA when the quality of study and previously attained performance were  ...  Next, high-school GPA and SAT scores were entered into the regression as indicators of prior knowledge and skills.  ... 
doi:10.1016/j.cedpsych.2004.06.001 fatcat:p4vcbzcuu5f2zj3yjobkvxmqd4

Context-aware Non-linear and Neural Attentive Knowledge-based Models for Grade Prediction [article]

Sara Morsy, George Karypis
2020 arXiv   pre-print
One of the successful approaches for accurately predicting a student's grades in future courses is Cumulative Knowledge-based Regression Models (CKRM).  ...  CKRM learns shallow linear models that predict a student's grades as the similarity between his/her knowledge state and the target course.  ...  Cumulative Knowledge-based Regression Models (CKRM) Morsy et al.  ... 
arXiv:2003.05063v1 fatcat:leyzugpnwfdlnkw2thwnafzwa4

Academic Performance Estimation with Attention-based Graph Convolutional Networks [article]

Qian Hu, Huzefa Rangwala
2019 arXiv   pre-print
The experimental results show that our proposed model outperforms state-of-the-art approaches in terms of grade prediction.  ...  In this work, we propose a novel attention-based graph convolutional networks model for student's performance prediction.  ...  Morsy et al. proposed cumulative knowledge-based regression models for next-term grade prediction, which models students' knowledge evolution by using a sequential regression model. Hu et al.  ... 
arXiv:2001.00632v1 fatcat:kuh2uifuavh4jjlzehebvoy74i

A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs

Jie Xu, Kyeong Ho Moon, Mihaela van der Schaar
2017 IEEE Journal on Selected Topics in Signal Processing  
Second, a data-driven approach based on latent factor models and probabilistic matrix factorization is proposed to discover course relevance, which is important for constructing efficient base predictors  ...  First, a bilayered structure comprising of multiple base predictors and a cascade of ensemble predictors is developed for making predictions based on students' evolving performance states.  ...  The next question is how to make predictions using these base predictors for new students. There would not be any problem if there were just one term, i.e. T = 1 and one base predictor, i.e. H = 1.  ... 
doi:10.1109/jstsp.2017.2692560 fatcat:xjw6zcb4s5gfbafmlp7ve4aw2y

Context-aware Nonlinear and Neural Attentive Knowledge-based Models for Grade Prediction

Sara Morsy, George Karypis
2020 Zenodo  
One of the successful approaches for accu- rately predicting a student's grades in future courses is Cumulative Knowledge-based Regression Models (CKRM).  ...  CKRM learns shallow linear models that predict a student's grades as the similarity between his/her knowledge state and the target course.  ...  Cumulative Knowledge-based Regression Models (CKRM) Morsy and Karypis (2017) developed Cumulative Knowledge-based Regression Models (CKRM), which also models a student's performance in a future course  ... 
doi:10.5281/zenodo.3911794 fatcat:cxcfo556uzeixndpnsxoledu6i

Identifying Medical Students Likely to Exhibit Poor Professionalism and Knowledge During Internship

David L. Greenburg, Steven J. Durning, Daniel L. Cohen, David Cruess, Jeffrey L. Jackson
2007 Journal of general internal medicine  
Multivariable logistic regression modeling revealed that grades earned during the third year predicted low ratings in both knowledge (odds ratio [OR]=4.9; 95%CI=2.7-9.2) and professionalism (OR= 7.3; 95%  ...  The predictive ability for the knowledge and professionalism models was modest (respective area under ROC curves=0.735 and 0.725).  ...  Figure 1 . 1 ROC curves for multivariable logistic regression models predicting intern knowledge ratings. Solid blue line represents the third year GPA and step 1; area under ROC curve=.735.  ... 
doi:10.1007/s11606-007-0405-z pmid:17952512 pmcid:PMC2219838 fatcat:2mrceclzlbaylmueo5xmno7uzq

Student Ability Best Predicts Final Grade in a College Algebra Course

Kyle O'Connell, Elijah Wostl, Matt Crosslin, T. Lisa Berry, James P. Grover
2018 Journal of Learning Analytics  
We find that indicators of students' past performance and experience, including grade-point-average and the number of accumulated credit hours, best predict student success in this course.  ...  Notes for Practice • Past studies have found that student grades are influenced by several factors, including student ability, student demographic background, and course specific factors. • This study  ...  The program predicted the fit of the best model as a percentage based on the AICC score of that model.  ... 
doi:10.18608/jla.2018.53.11 fatcat:qbhyetwoxzco3afmj2drtvibwi

Grade Prediction with Course and Student Specific Models [chapter]

Agoritsa Polyzou, George Karypis
2016 Lecture Notes in Computer Science  
This paper presents future-course grade predictions methods based on sparse linear models and low-rank matrix factorizations that are specific to each course or student-course tuple.  ...  This evaluation showed that the course-specific models outperformed various competing schemes with the best performing scheme achieving an RMSE across the different courses of 0.632 vs 0.661 for the best  ...  next term, and create personalized degree pathways that enable them to successfully and effectively acquire the required knowledge to complete their studies in a timely fashion.  ... 
doi:10.1007/978-3-319-31753-3_8 fatcat:tolltodejzdqtdrdgbf4di7m3u

SmartGPA

Rui Wang, Gabriella Harari, Peilin Hao, Xia Zhou, Andrew T. Campbell
2015 Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing - UbiComp '15  
We propose a simple model based on linear regression with lasso regularization that can accurately predict cumulative GPA.  ...  The predicted GPA strongly correlates with the ground truth from students' transcripts (r = 0.81 and p < 0.001) and predicts GPA within ±0.179 of the reported grades.  ...  The spring term GPA captures how a student performs in a single 10-week term. After correlation analysis we discuss our model for predicting cumulative GPA.  ... 
doi:10.1145/2750858.2804251 dblp:conf/huc/WangHHZC15 fatcat:wuncwn5lo5a3fg5av3ctgzzitu
« Previous Showing results 1 — 15 out of 27,542 results