To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Algorithms for Classifying the Results at the Baccalaureate Exam - Comparative Analysis of Performances |
|
Author |
Daniela Marcu, Mirela Danubianu, Adina B?r?l? and Corina Simionescu |
| Citation |
Vol. 21 No. 8 pp. 35-42 |
|
Abstract |
In the current context of digitalization of education, the use of modern methods and techniques of data analysis and processing in order to improve students' school results has a very important role. In our paper, we aimed to perform a comparative study of the classification performances of AdaBoost, SVM, Naive Bayes, Neural Network and kNN algorithms to classify the results obtained at the Baccalaureate by students from a college in Suceava, during 2012-2019. To evaluate the results we used the metrics: AUC, CA, F1, Precision and Recall. The AdaBoost algorithm achieves incredible performance for classifying the results into two categories: promoted / rejected. Next in terms of performance is Naive Bayes with a score of 0.999 for the AUC metric. The Neural Network and kNN algorithms obtain scores of 0.998 and 0.996 for AUC, respectively. SVM shows poorer performance with the score 0.987 for AUC. With the help of the HeatMap and DataTable visualization tools we identified possible correlations between classification results and some characteristics of data. |
|
Keywords |
Classification algorithms, data visualization. |
|
URL |
