Grade prediction with models specific to students and courses

Polyzou, Agoritsa; Karypis, George

doi:10.1007/s41060-016-0024-z

Cited by 67 publications

(51 citation statements)

References 16 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. [14], we compute the Percentage of Tick Accuracy (PTA). First, we define a tick as the difference between two consecutive letter grades (e.g., C+ vs C or C vs C-).…”

Section: Evaluation Metricsmentioning

confidence: 99%

ALE: Additive Latent Effect Models for Grade Prediction

Ren

Ning

Rangwala

2018

Proceedings of the 2018 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

The past decade has seen a growth in the development and deployment of educational technologies for assisting college-going students in choosing majors, selecting courses and acquiring feedback based on past academic performance. 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). Accurate and timely prediction of students' academic grades is important for developing effective degree planners and early warning systems, and ultimately improving educational outcomes. Existing grade prediction methods mostly focus on modeling the knowledge components associated with each course and student, and often overlook other factors such as the difficulty of each knowledge component, course instructors, student interest, capabilities and effort.In this paper, we propose additive latent effect models that incorporate these factors to predict the student next-term grades. Specifically, the proposed models take into account four factors: (i) student's academic level, (ii) course instructors, (iii) student global latent factor, and (iv) latent knowledge factors. We compared the new models with several state-of-the-art methods on students of various characteristics (e.g., whether a student transferred in or not). The experimental results demonstrate that the proposed methods significantly outperform the baselines on grade prediction problem. Moreover, we perform a thorough analysis on the importance of different factors and how these factors can practically assist students in course selection, and finally improve their academic performance.

show abstract

“…al. [14], we compute the Percentage of Tick Accuracy (PTA). First, we define a tick as the difference between two consecutive letter grades (e.g., C+ vs C or C vs C-).…”

Section: Evaluation Metricsmentioning

confidence: 99%

ALE: Additive Latent Effect Models for Grade Prediction

Ren

Ning

Rangwala

2018

Proceedings of the 2018 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

show abstract

“…These approaches use a one-size-fits-all framework for training the model and prediction. Polyzou et al proposed a personalized model that is specific to each course and student [28]. Student-course enrollment patterns have grouping structures which result in missing not at random patterns of student grade data.…”

Section: Student Performance Predictionmentioning

confidence: 99%

“…Given a student's grades in the courses taken before the target course (referred to as prior courses), the objective of the next-term grade prediction problem is to predict the grade that the student will achieve in a course to be taken in the next semester (term). To predict grade in a course-wise manner, we adopt course-specific framework [28]. Under this framework, different models are learnt for different courses.…”

Section: Model Learning Frameworkmentioning

confidence: 99%

“…Courses. The coursespecific regression with prior courses (CSR PC ) [28] predicts the grade of a student s in a course c as a linear combination of the grades in prior courses.…”

Section: Course-specific Regression With Priormentioning

confidence: 99%

“…However, different courses have different characteristics such as prerequisites, knowledge content, instructors and difficulty level. To address this problem, Polyzou et al proposed a course-specific framework, which was shown to be successful for accurately predicting students' grades [27,28]. Course-specific methods identify a subsets of prior courses on a course-by-course basis to predict a student's grade in a target course.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reliable Deep Grade Prediction with Uncertainty Estimation

Rangwala

2019

Proceedings of the 9th International Conference on Learning Analytics &Amp; Knowledge

View full text Add to dashboard Cite

Currently, college-going students are taking longer to graduate than their parental generations. Further, in the United States, the six-year graduation rate has been 59% for decades. Improving the educational quality by training better-prepared students who can successfully graduate in a timely manner is critical. Accurately predicting students' grades in future courses has attracted much attention as it can help identify at-risk students early so that personalized feedback can be provided to them on time by advisors. Prior research on students' grade prediction include shallow linear models; however, students' learning is a highly complex process that involves the accumulation of knowledge across a sequence of courses that can not be sufficiently modeled by these linear models. In addition to that, prior approaches focus on prediction accuracy without considering prediction uncertainty, which is essential for advising and decision making. In this work, we present two types of Bayesian deep learning models for grade prediction under a course-specific framework: i)Multilayer Perceptron (MLP) and ii) Recurrent Neural Network (RNN). These course-specific models are based on the assumption that prior courses can provide students with knowledge for future courses so that grades of prior courses can be used to predict grades in a future course. The MLP ignores the temporal dynamics of students' knowledge evolution. Hence, we propose RNN for students' performance prediction. To evaluate the performance of the proposed models, we performed extensive experiments on data collected from a large public university. The experimental results show that the proposed models achieve better performance than prior state-of-the-art approaches. Besides more accurate results, Bayesian deep learning models estimate uncertainty associated with the predictions. We explore how uncertainty estimation can be applied towards developing a reliable educational early warning system. In addition to uncertainty, we also develop an approach to explain the prediction results, which is useful for advisors to provide personalized feedback to students.

show abstract