Abstract | ||
---|---|---|
We present a new probabilistic model to predict the graduation rates of universities. For this purpose this model uses the geometric distribution augmented with item response theory. In particular it uses four main variables for prediction: high school GPA, ACT/SAT score, course difficulty and curriculum complexity. The records of 10,479 students from the University of New Mexico (UNM) were used to train the model. The results presented in this paper show the type of correlation between these variables and graduation rates. They also show the prediction accuracy of our proposed model. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTED, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION (SMARTWORLD/SCALCOM/UIC/ATC/CBDCOM/IOP/SCI) | Geometric distribution, item response theory, education, curriculum complexity, graduation rate, data mining, data analytics |
Field | DocType | Citations |
Grading (education),Computer science,Theoretical computer science,Correlation,Curriculum,Statistical model,Geometric distribution,Probabilistic logic,Item response theory,Distributed computing | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ahmad Slim | 1 | 53 | 5.89 |
G L Heileman | 2 | 71 | 4.90 |
Michael Hickman | 3 | 0 | 0.34 |
Chaouki T. Abdallah | 4 | 209 | 34.98 |