Análisis de técnicas de agrupamiento para detección de valores anómalos en rendimiento estudiantil en una institución de educación superior

Angelo Isaac  Iturralde Borja; Patricia Jimbo Santana

Análisis de técnicas de agrupamiento para detección de valores anómalos en rendimiento estudiantil en una institución de educación superior

Autores/as

Angelo Isaac Iturralde Borja Universidad Central del Ecuador
Patricia Jimbo Santana Universidad Central del Ecuador

Resumen

En las universidades, la gestión de datos enfrenta riesgos significativos debido al desconocimiento generalizado. Sin embargo, la recolección y el análisis de estos datos son fundamentales para garantizar una enseñanza de calidad y la transparencia en los procesos académicos. A menudo, se presentan irregularidades en el registro de las calificaciones de los estudiantes, ya sea por errores involuntarios, intentos de fraude o actos de corrupción. En este artículo, aplicamos técnicas de clusterización, específicamente el método "K-means", para detectar estos posibles casos de manera oportuna. Esta metodología se basa en la capacidad de identificar valores o datos anómalos, lo que permite mejorar la detección de incidentes y proporciona una herramienta eficaz para el control y la supervisión de los registros académicos.Además, estas técnicas pueden utilizarse para optimizar la precisión de los procesos de evaluación, mejorando así la calidad de la información disponible para la toma de decisiones. Esto facilita la implementación de medidas correctivas oportunas, reduciendo el riesgo de que errores o malas prácticas afecten tanto el rendimiento académico de los estudiantes como la reputación de la institución.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Abe, K. (2019). Data Mining and Machine Learning Applications for Educational Big Data in the University. 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), 350–355. https://doi.org/10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00071

Agarwal, Amit. (2015). Proceedings on 2015 1st International Conference on Next Generation Computing Technologies (NGCT) : September 4th-5th, 2015, Center for Information Technology, University of Petroleum and Energy Studies, Dehradun. IEEE.

Agarwal, S. (2014). Data mining: Data mining concepts and techniques. Proceedings - 2013 International Conference on Machine Intelligence Research and Advancement, ICMIRA 2013, 203–207. https://doi.org/10.1109/ICMIRA.2013.45

Bae, D. H., Jeong, S., Hong, J., Lee, M., Ivanović, M., Savić, M., & Kim, S. W. (2020). An Effective Approach to Outlier Detection Based on Centrality and Centre-Proximity. Informatica (Netherlands), 31(3), 435–458. https://doi.org/10.15388/20-INFOR413

Devasia, M. T., Vinushree, M., & Hegde, M. V. (n.d.). Prediction of Students Performance using Educational Data Mining.

Dol, S. M. (2021, January 15). Use of Classification Technique in Educational Data Mining. 2021 International Conference on Nascent Technologies in Engineering, ICNET 2021 - Proceedings. https://doi.org/10.1109/ICNTE51185.2021.9487739

Dol, S. M., & Jawandhiya, P. M. (2022). Use of Data mining Tools in Educational Data Mining. Proceedings - 2022 5th International Conference on Computational Intelligence and Communication Technologies, CCICT 2022, 380–387. https://doi.org/10.1109/CCiCT56684.2022.00075

Hidayat, N., Wardoyo, R., & Sn, A. (n.d.). Educational Data Mining (EDM) as a Model for Students’ Evaluation in Learning Environment.

J Md Zubair Rahman Principal, A. M. (n.d.). A Review on Data Mining Techniques and Factors Used in Educational Data Mining to Predict Student Amelioration.

J. Yao, J. Z. and L. W. (2018). A financial statement fraud detection model based on hybrid data mining methods. IEEE Press. https://doi.org/10.1109/ICAIBD.2018.8396167

Kanjanawattana, S. (2019). A novel outlier detection applied to an adaptive K-means. International Journal of Machine Learning and Computing, 9(5), 569–574. https://doi.org/10.18178/ijmlc.2019.9.5.841

Kültür, Y., & Ufuk Çağlayan, M. (n.d.). A Novel Cardholder Behavior Model for Detecting Credit Card Fraud.

Lakshmi Sreenivasa Reddy.D, S.Sailaja, Vijaya Bhaskar Velpula, & Dr.B.Raveendrababu2. (2014). Finding Peculiar Students from Student Database using Outlier Analysis: Data Mining Approach. Institute of Electrical and Electronics Engineers (IEEE).

Min, X., & Lin, R. (2018). K-means algorithm: Fraud detection based on signaling data. Proceedings - 2018 IEEE World Congress on Services, SERVICES 2018, 23–24. https://doi.org/10.1109/SERVICES.2018.00024

Muhammed, L. A. N. (2021). Educational Data Mining: Analyzing Teacher Behavior based Student’s Performance. Proceedings - 2021 4th International Conference on Computer and Informatics Engineering: IT-Based Digital Industrial Innovation for the Welfare of Society, IC2IE 2021, 181–185. https://doi.org/10.1109/IC2IE53219.2021.9649366

Pamula, R., Deka, J. K., & Nandi, S. (2011). An outlier detection method based on clustering. Proceedings - 2nd International Conference on Emerging Applications of Information Technology, EAIT 2011, 253–256. https://doi.org/10.1109/EAIT.2011.25

Peng’, Y., Kou, G., Sabatka2, A., Chen’, Z., Khazanchil, D., & Shi3, Y. (n.d.). Application of Clustering Methods to Health Insurance Fraud Detection.

Poonam, & Dutta, M. (2012). Performance analysis of clustering methods for outlier detection. Proceedings - 2012 2nd International Conference on Advanced Computing and Communication Technologies, ACCT 2012, 89–95. https://doi.org/10.1109/ACCT.2012.84

Pornthep Rojanavasu. (2019). Educational Data Analytics using Association Rule Mining and Classification. IEEE.

Pramanik, A., Sarker, A., Islam, Z., & Hashem, M. M. A. (2020). Public sector corruption analysis with modified K-means algorithm using perception data. Proceedings of 2020 11th International Conference on Electrical and Computer Engineering, ICECE 2020, 198–201. https://doi.org/10.1109/ICECE51571.2020.9393110

Sagardeep Roy, & Shailendra Narayan Singh. (2017). Emerging Trends in Applications of Big Data in Educational Data Mining and Learning Analytics. IEEE.

Venkatachalapathy, K., Vijayalakshmi, V., & Ohmprakash, V. (2017). Educational data mining tools: A survey from 2001 to 2016. Proceedings - 2017 2nd International Conference on Recent Trends and Challenges in Computational Models, ICRTCCM 2017, 67–72. https://doi.org/10.1109/ICRTCCM.2017.53