Academic Performance: An Approach From Data Mining
The relatively low% of students promoted and regularized in Operating Systems Course of the LSI (Bachelor’s Degree in Information Systems) of FaCENA (Faculty of Sciences and Natural Surveying - Facultad de Ciencias Exactas, Naturales y Agrimensura) of UNNE (academic success), prompted this work, who...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
International Institute of Informatics and Cybernetics
2012-02-01
|
Series: | Journal of Systemics, Cybernetics and Informatics |
Subjects: | |
Online Access: | http://www.iiisci.org/Journal/CV$/sci/pdfs/HFB525EV.pdf
|
_version_ | 1811276564753547264 |
---|---|
author | David L. La Red Martinez Julio C. Acosta Valeria E. Uribe Alice R. Rambo |
author_facet | David L. La Red Martinez Julio C. Acosta Valeria E. Uribe Alice R. Rambo |
author_sort | David L. La Red Martinez |
collection | DOAJ |
description | The relatively low% of students promoted and regularized in Operating Systems Course of the LSI (Bachelor’s Degree in Information Systems) of FaCENA (Faculty of Sciences and Natural Surveying - Facultad de Ciencias Exactas, Naturales y Agrimensura) of UNNE (academic success), prompted this work, whose objective is to determine the variables that affect the academic performance, whereas the final status of the student according to the Res. 185/03 CD (scheme for evaluation and promotion): promoted, regular or free1. The variables considered are: status of the student, educational level of parents, secondary education, socio-economic level, and others. Data warehouse (Data Warehouses: DW) and data mining (Data Mining: DM) techniques were used to search pro.les of students and determine success or failure academic potential situations. Classifications through techniques of clustering according to different criteria have become. Some criteria were the following: mining of classification according to academic program, according to final status of the student, according to importance given to the study, mining of demographic clustering and Kohonen clustering according to final status of the student. Were conducted statistics of partition, detail of partitions, details of clusters, detail of fields and frequency of fields, overall quality of each process and quality detailed (precision, classification, reliability), arrays of confusion, diagrams of gain / elevation, trees, distribution of nodes, of importance of fields, correspondence tables of fields and statistics of cluster. Once certain profiles of students with low academic performance, it may address actions aimed at avoiding potential academic failures. This work aims to provide a brief description of aspects related to the data warehouse built and some processes of data mining developed on the same. |
first_indexed | 2024-04-12T23:58:50Z |
format | Article |
id | doaj.art-21ee81b99bd9469a9e3a55b49c7c7610 |
institution | Directory Open Access Journal |
issn | 1690-4524 |
language | English |
last_indexed | 2024-04-12T23:58:50Z |
publishDate | 2012-02-01 |
publisher | International Institute of Informatics and Cybernetics |
record_format | Article |
series | Journal of Systemics, Cybernetics and Informatics |
spelling | doaj.art-21ee81b99bd9469a9e3a55b49c7c76102022-12-22T03:11:24ZengInternational Institute of Informatics and CyberneticsJournal of Systemics, Cybernetics and Informatics1690-45242012-02-011016672Academic Performance: An Approach From Data MiningDavid L. La Red Martinez0Julio C. Acosta1Valeria E. Uribe2Alice R. Rambo3 Universidad Nacional del Nordeste Universidad Nacional del Nordeste Universidad Nacional del Nordeste Universidad Nacional del Nordeste The relatively low% of students promoted and regularized in Operating Systems Course of the LSI (Bachelor’s Degree in Information Systems) of FaCENA (Faculty of Sciences and Natural Surveying - Facultad de Ciencias Exactas, Naturales y Agrimensura) of UNNE (academic success), prompted this work, whose objective is to determine the variables that affect the academic performance, whereas the final status of the student according to the Res. 185/03 CD (scheme for evaluation and promotion): promoted, regular or free1. The variables considered are: status of the student, educational level of parents, secondary education, socio-economic level, and others. Data warehouse (Data Warehouses: DW) and data mining (Data Mining: DM) techniques were used to search pro.les of students and determine success or failure academic potential situations. Classifications through techniques of clustering according to different criteria have become. Some criteria were the following: mining of classification according to academic program, according to final status of the student, according to importance given to the study, mining of demographic clustering and Kohonen clustering according to final status of the student. Were conducted statistics of partition, detail of partitions, details of clusters, detail of fields and frequency of fields, overall quality of each process and quality detailed (precision, classification, reliability), arrays of confusion, diagrams of gain / elevation, trees, distribution of nodes, of importance of fields, correspondence tables of fields and statistics of cluster. Once certain profiles of students with low academic performance, it may address actions aimed at avoiding potential academic failures. This work aims to provide a brief description of aspects related to the data warehouse built and some processes of data mining developed on the same.http://www.iiisci.org/Journal/CV$/sci/pdfs/HFB525EV.pdf Data MiningCluster DemographicClusteringdatabaseOperating SystemsProfiles Of StudentsData WarehouseAcademic Performance |
spellingShingle | David L. La Red Martinez Julio C. Acosta Valeria E. Uribe Alice R. Rambo Academic Performance: An Approach From Data Mining Journal of Systemics, Cybernetics and Informatics Data Mining Cluster Demographic Clustering database Operating Systems Profiles Of Students Data Warehouse Academic Performance |
title | Academic Performance: An Approach From Data Mining |
title_full | Academic Performance: An Approach From Data Mining |
title_fullStr | Academic Performance: An Approach From Data Mining |
title_full_unstemmed | Academic Performance: An Approach From Data Mining |
title_short | Academic Performance: An Approach From Data Mining |
title_sort | academic performance an approach from data mining |
topic | Data Mining Cluster Demographic Clustering database Operating Systems Profiles Of Students Data Warehouse Academic Performance |
url | http://www.iiisci.org/Journal/CV$/sci/pdfs/HFB525EV.pdf
|
work_keys_str_mv | AT davidllaredmartinez academicperformanceanapproachfromdatamining AT juliocacosta academicperformanceanapproachfromdatamining AT valeriaeuribe academicperformanceanapproachfromdatamining AT alicerrambo academicperformanceanapproachfromdatamining |