PROPOSAL OF A TIME SERIES-BASED MODEL FOR THE CHARACTERIZATION AND PREDICTION OF DROPOUT RATES AT THE NATIONAL OPEN AND DISTANCE UNIVERSITY.
Saved in:
| Title: | PROPOSAL OF A TIME SERIES-BASED MODEL FOR THE CHARACTERIZATION AND PREDICTION OF DROPOUT RATES AT THE NATIONAL OPEN AND DISTANCE UNIVERSITY. |
|---|---|
| Alternate Title: | PROPUESTA DE UN MODELO BASADO EN SERIES TEMPORALES PARA LA CARACTERIZACIÓN Y PREDICCIÓN DE LAS TASAS DE DESERCIÓN EN LA UNIVERSIDAD NACIONAL ABIERTA Y A DISTANCIA. |
| Authors: | Chanchí G., Gabriel Elías1 gchanchig@unicartagena.edu.co, Monroy Gómez, Luis Fernando2 lfmonroyg@unadvirtual.edu.co, Barrera Buitrago, Dayana Alejandra3 dayana.barrera@unad.edu.co |
| Source: | Revista Ingenierías Universidad de Medellin. Jan-Jun2024, Vol. 23 Issue 44, p1-17. 17p. |
| Subjects: | Time series analysis, Educational indicators, School dropout prevention, Educational quality, RF values (Chromatography) |
| Abstract (English): | Dropout rates are a key indicator of educational quality, making it imperative for educational institutions to design strategies to reduce them, thereby contributing to improved student retention and the achievement of academic objectives. While dropout research has primarily focused on machine learning methods applied to in-person education datasets, this article introduces a novel approach based on time series models for dropout rates analysis at the National Open and Distance University (UNAD). Methodologically, an adaptation of the CRISP-DM methodology was undertaken in four phases, namely: F1. Business and data understanding, F2. Data preparation, F3. Model building and evaluation, and F4. Model deployment. In terms of results, an open dataset on UNAD dropout, obtained from the SPADIES system between 1999 and 2021, was employed. Using Python libraries statsmodels and pandas, an ARIMA model was implemented, displaying optimal error metrics. This ARIMA model was utilized to forecast future dropout rates at UNAD, projecting a future dropout rate fluctuating around 23%. In conclusion, the ARIMA model developed for UNAD stands as an innovative and essential tool in the educational realm, capable of accurately anticipating dropout rates for upcoming semesters. This provides UNAD with a unique advantage in strategic decision-making. [ABSTRACT FROM AUTHOR] |
| Abstract (Spanish): | La tasa de deserción es un indicador clave de la calidad educativa, por lo que es imperativo que las instituciones educativas diseñen estrategias para reducirla y así aumentar la retención estudiantil y alcanzar los logros académicos. Mientras que la investigación sobre la deserción se ha concentrado principalmente en métodos de aprendizaje automático aplicados a conjuntos de datos sobre educación presencial, este artículo introduce un enfoque novedoso al utilizar modelos de series temporales para analizar la tasa de deserción de la Universidad Nacional Abierta y a Distancia (UNAD). En cuanto a la metodología, se adaptó el proceso CRISP-DM en cuatro fases, a saber: F1. Comprensión del negocio y de los datos, F2. Preparación de los datos. F3. Modelado y evaluación y F4. Despliegue del modelo. Respecto a los resultados, se empleó un conjunto de datos abiertos sobre la deserción en la UNAD que abarca desde 1999 hasta 2021, el cual se obtuvo del sistema SPADIES. Mediante el uso de las bibliotecas de Python statsmodels y pandas, se implementó un modelo ARIMA, el cual arrojó excelentes resultados en las medidas de error. Este modelo ARIMA se utilizó para predecir la tasa de deserción futura de la UNAD, la cual se proyecta que oscilará alrededor del 23 %. En conclusión, el modelo ARIMA desarrollado para la UNAD se destaca como una herramienta innovadora y fundamental en el ámbito educativo, capaz de predecir de forma precisa la tasa de deserción de semestres futuros, lo cual le otorga a la UNAD una ventaja única en la toma decisiones estratégicas. [ABSTRACT FROM AUTHOR] |
| Copyright of Revista Ingenierías Universidad de Medellin is the property of Universidad de Medellin and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 178830772 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: PROPOSAL OF A TIME SERIES-BASED MODEL FOR THE CHARACTERIZATION AND PREDICTION OF DROPOUT RATES AT THE NATIONAL OPEN AND DISTANCE UNIVERSITY. – Name: TitleAlt Label: Alternate Title Group: TiAlt Data: PROPUESTA DE UN MODELO BASADO EN SERIES TEMPORALES PARA LA CARACTERIZACIÓN Y PREDICCIÓN DE LAS TASAS DE DESERCIÓN EN LA UNIVERSIDAD NACIONAL ABIERTA Y A DISTANCIA. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chanchí+G%2E%2C+Gabriel+Elías%22">Chanchí G., Gabriel Elías</searchLink><relatesTo>1</relatesTo><i> gchanchig@unicartagena.edu.co</i><br /><searchLink fieldCode="AR" term="%22Monroy+Gómez%2C+Luis+Fernando%22">Monroy Gómez, Luis Fernando</searchLink><relatesTo>2</relatesTo><i> lfmonroyg@unadvirtual.edu.co</i><br /><searchLink fieldCode="AR" term="%22Barrera+Buitrago%2C+Dayana+Alejandra%22">Barrera Buitrago, Dayana Alejandra</searchLink><relatesTo>3</relatesTo><i> dayana.barrera@unad.edu.co</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Revista+Ingenierías+Universidad+de+Medellin%22">Revista Ingenierías Universidad de Medellin</searchLink>. Jan-Jun2024, Vol. 23 Issue 44, p1-17. 17p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Time+series+analysis%22">Time series analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Educational+indicators%22">Educational indicators</searchLink><br /><searchLink fieldCode="DE" term="%22School+dropout+prevention%22">School dropout prevention</searchLink><br /><searchLink fieldCode="DE" term="%22Educational+quality%22">Educational quality</searchLink><br /><searchLink fieldCode="DE" term="%22RF+values+%28Chromatography%29%22">RF values (Chromatography)</searchLink> – Name: Abstract Label: Abstract (English) Group: Ab Data: Dropout rates are a key indicator of educational quality, making it imperative for educational institutions to design strategies to reduce them, thereby contributing to improved student retention and the achievement of academic objectives. While dropout research has primarily focused on machine learning methods applied to in-person education datasets, this article introduces a novel approach based on time series models for dropout rates analysis at the National Open and Distance University (UNAD). Methodologically, an adaptation of the CRISP-DM methodology was undertaken in four phases, namely: F1. Business and data understanding, F2. Data preparation, F3. Model building and evaluation, and F4. Model deployment. In terms of results, an open dataset on UNAD dropout, obtained from the SPADIES system between 1999 and 2021, was employed. Using Python libraries statsmodels and pandas, an ARIMA model was implemented, displaying optimal error metrics. This ARIMA model was utilized to forecast future dropout rates at UNAD, projecting a future dropout rate fluctuating around 23%. In conclusion, the ARIMA model developed for UNAD stands as an innovative and essential tool in the educational realm, capable of accurately anticipating dropout rates for upcoming semesters. This provides UNAD with a unique advantage in strategic decision-making. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Abstract (Spanish) Group: Ab Data: La tasa de deserción es un indicador clave de la calidad educativa, por lo que es imperativo que las instituciones educativas diseñen estrategias para reducirla y así aumentar la retención estudiantil y alcanzar los logros académicos. Mientras que la investigación sobre la deserción se ha concentrado principalmente en métodos de aprendizaje automático aplicados a conjuntos de datos sobre educación presencial, este artículo introduce un enfoque novedoso al utilizar modelos de series temporales para analizar la tasa de deserción de la Universidad Nacional Abierta y a Distancia (UNAD). En cuanto a la metodología, se adaptó el proceso CRISP-DM en cuatro fases, a saber: F1. Comprensión del negocio y de los datos, F2. Preparación de los datos. F3. Modelado y evaluación y F4. Despliegue del modelo. Respecto a los resultados, se empleó un conjunto de datos abiertos sobre la deserción en la UNAD que abarca desde 1999 hasta 2021, el cual se obtuvo del sistema SPADIES. Mediante el uso de las bibliotecas de Python statsmodels y pandas, se implementó un modelo ARIMA, el cual arrojó excelentes resultados en las medidas de error. Este modelo ARIMA se utilizó para predecir la tasa de deserción futura de la UNAD, la cual se proyecta que oscilará alrededor del 23 %. En conclusión, el modelo ARIMA desarrollado para la UNAD se destaca como una herramienta innovadora y fundamental en el ámbito educativo, capaz de predecir de forma precisa la tasa de deserción de semestres futuros, lo cual le otorga a la UNAD una ventaja única en la toma decisiones estratégicas. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Revista Ingenierías Universidad de Medellin is the property of Universidad de Medellin and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=178830772 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.22395/rium.v23n44a7 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 1 Subjects: – SubjectFull: Time series analysis Type: general – SubjectFull: Educational indicators Type: general – SubjectFull: School dropout prevention Type: general – SubjectFull: Educational quality Type: general – SubjectFull: RF values (Chromatography) Type: general Titles: – TitleFull: PROPOSAL OF A TIME SERIES-BASED MODEL FOR THE CHARACTERIZATION AND PREDICTION OF DROPOUT RATES AT THE NATIONAL OPEN AND DISTANCE UNIVERSITY. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chanchí G., Gabriel Elías – PersonEntity: Name: NameFull: Monroy Gómez, Luis Fernando – PersonEntity: Name: NameFull: Barrera Buitrago, Dayana Alejandra IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Text: Jan-Jun2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 16923324 Numbering: – Type: volume Value: 23 – Type: issue Value: 44 Titles: – TitleFull: Revista Ingenierías Universidad de Medellin Type: main |
| ResultId | 1 |
