<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The widespread adoption of higher education has led to a continuous increase in the number of college graduates. Concurrently, the challenge of graduate unemployment is escalating, highlighting a critical need for precise career planning and guidance. Addressing the challenges faced by college graduates, this study employs the RFM model in conjunction with the fuzzy C-means clustering technique to categorize student data into distinct attributes. Subsequently, a GM(1,1) model is developed based on these attributes to forecast the future employment decisions of the students in the sample. The analysis reveals that the student data can be segmented into six distinct attributes. Of these, academic performance, English proficiency, and attributes related to physical and mental development, as well as cultural, sports, and artistic engagement, are identified as having greater significance. Notably, academic performance holds the highest importance, with a weight of 7.2. The GM(1,1) model demonstrates over 85% accuracy in predicting the future career choices of students. Despite minor discrepancies in certain areas of the model, its effectiveness is substantiated. The classification of attributes and the prediction of employment directions are poised to significantly enhance the development of targeted counseling strategies for college graduates facing employment difficulties. This approach not only aids in addressing immediate employment challenges but also contributes to the broader discourse on enhancing graduate employability through tailored guidance and support.</p>
</abstract>

The widespread adoption of higher education has led to a continuous increase in the number of college graduates. Concurrently, the challenge of graduate unemployment is escalating, highlighting a critical need for precise career planning and guidance. Addressing the challenges faced by college graduates, this study employs the RFM model in conjunction with the fuzzy C-means clustering technique to categorize student data into distinct attributes. Subsequently, a GM(1,1) model is developed based on these attributes to forecast the future employment decisions of the students in the sample. The analysis reveals that the student data can be segmented into six distinct attributes. Of these, academic performance, English proficiency, and attributes related to physical and mental development, as well as cultural, sports, and artistic engagement, are identified as having greater significance. Notably, academic performance holds the highest importance, with a weight of 7.2. The GM(1,1) model demonstrates over 85% accuracy in predicting the future career choices of students. Despite minor discrepancies in certain areas of the model, its effectiveness is substantiated. The classification of attributes and the prediction of employment directions are poised to significantly enhance the development of targeted counseling strategies for college graduates facing employment difficulties. This approach not only aids in addressing immediate employment challenges but also contributes to the broader discourse on enhancing graduate employability through tailored guidance and support.

Research on the construction of accurate counseling path for students with employment difficulties in colleges and universities based on RFM model analysis

Xi’an University of Science and Technology

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The widespread adoption of higher education has led to a continuous increase in the number of college graduates. Concurrently, the challenge of graduate...

Research on the construction of accurate counseling path for students with employment difficulties in colleges and universities based on RFM model analysis

Publié en ligne: 05 août 2024

Pages: -

Reçu: 25 mars 2024

Accepté: 21 juin 2024

DOI: https://doi.org/10.2478/amns-2024-1857

Mots clés
Employment counseling, RFM model, Mean clustering, GM(1,1) model

© 2024 Yi Li., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on the construction of accurate counseling path for students with employment difficulties in colleges and universities based on RFM model analysis

Publié en ligne: 05 août 2024

Pages: -

Reçu: 25 mars 2024

Accepté: 21 juin 2024

DOI: https://doi.org/10.2478/amns-2024-1857

Mots clésEmployment counseling, RFM model, Mean clustering, GM(1,1) model

© 2024 Yi Li., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Employment counseling, RFM model, Mean clustering, GM(1,1) model