A Novel CatML Stacking Classifier Based Intelligent System for Predicting Postgraduate Admission Chances: A Study on Bangladesh

PDF (1354KB), PP.82-100

Views: 0 Downloads: 0

Author(s)

Abu Kowshir Bitto 1,* Md. Hasan Imam Bijoy 2 Aka Das 3 Jannatul Ferdousi 1 Afsana Begum 1 Imran Mahmud 1

1. Department of Software Engineering, Daffodil International University, Dhaka-1216, Bangladesh

2. Department of Computer Science and Engineering, Daffodil International University, Dhaka-1216, Bangladesh

3. Department of Computer Science and Engineering, Premier University, Chittagong-4203, Bangladesh

* Corresponding author.

DOI: https://doi.org/10.5815/ijmecs.2025.04.06

Received: 16 Sep. 2024 / Revised: 15 Apr. 2025 / Accepted: 18 May 2025 / Published: 8 Aug. 2025

Index Terms

Predictive Analytics, Postgraduate Admissions, Admission Probability, Intelligent Prediction Tool

Abstract

This paper introduces an intelligent tool with a novel CatML stacking classifier designed to enhance predictive analytics for postgraduate university admission chances. The proposed classifier uses the CatBoost algorithm as a core component of the stacking ensemble method, which integrates CatBoost and Multi-Layer Perceptron (MLP) learners to improve predictive performance. The dataset comprises 13 questionnaire-based surveys, including academic records, standardized test scores (i.e., GRE, IELTS/TOEFL), publication status, extracurricular activities, recommendation letters, and personal statements from Bangladeshi students who applied to various U.S. postgraduate programs. Experimental results demonstrate that the CatML stacking classifier outperforms conventional models, achieving superior accuracy (88.14%) and robustness in predicting admission outcomes. The enhanced performance is attributed to the model’s ability to capture complex, non-linear relationships within the data, facilitated by the CatBoost algorithm's handling of categorical features and prevention of overfitting. Finally, this model deploys in a web system developed with HTML, CSS, JavaScript and Flask. This research underscores the efficacy of advanced ensemble techniques in educational data mining and provides a valuable intelligent tool for students aiming to navigate the complexities of U.S. postgraduate admissions. The CatML stacking classifier offers significant improvements in predictive analytics, thereby assisting students in making informed application decisions.

Cite This Paper

Abu Kowshir Bitto, Md. Hasan Imam Bijoy, Aka Das, Jannatul Ferdousi, Afsana Begum, Imran Mahmud, "A Novel CatML Stacking Classifier Based Intelligent System for Predicting Postgraduate Admission Chances: A Study on Bangladesh", International Journal of Modern Education and Computer Science(IJMECS), Vol.17, No.4, pp. 82-100, 2025. DOI:10.5815/ijmecs.2025.04.06

Reference

[1]Ewa Krzaklewska, “Why Study Abroad? – An Analysis of Erasmus Students’ Motivation,” Students, Staff Acad. Mobil. High. Educ., pp. 82–98, 2008.
[2]C. U. Zachrisson, “New Study Abroad Destinations : Trends and Emerging Opportunities,” pp. 28–30, 1998.
[3]G. Maharaja, “The Impact of Study Abroad on College Students’ Intercultural Competence and Personal Development,” Int. Res. Rev. J. Phi Beta Delta Honor Soc. Int. Sch., vol. 7, no. 2, pp. 18–41, 2018.
[4]A. Sarreiro, “This electronic thesis or dissertation has been downloaded from Explore Bristol Research , Author : A thesis submitted to the University of Bristol in accordance with the University of Bristol School of Geographical Sciences,” 2019.
[5]R. M. Paige, G. W. Fry, E. M. Stallman, J. Josić, and J. Jon, “Study abroad for global engagement: the long‐term impact of mobility experiences,” Intercult. Educ., vol. 20, no. sup1, pp. S29–S44, 2009, doi: 10.1080/14675980903370847.
[6]Chowdhury, Shanjida, Md Fouad Hossain Sarker, Niaz Ahmed Khan, Md Kabirul Islam, Maruf Ahmed Tamal, and Md Hasan Imam Bijoy. "Students’ Satisfaction in Online Class during COVID‐19: An Empirical Study in Bangladesh Context." Education Research International 2024, no. 1 (2024): 1333227.
[7]S. Deloach, L. Saliba, V. Smith, and T. Tiemann, “Developing a global mindset through short-term study abroad: A group discussion approach,” J. Teach. Int. Bus., vol. 15, no. 1, pp. 37–59, 2003, doi: 10.1300/J066v15n01_04.
[8]B. A. Z. Zielinski, “Study Abroad Length of Program Influence on Cross-Cultural Adaptability,” p. 66, 2007.
[9]S. Nicholls, “Influences on international student choice of study destination: Evidence from the United States,” J. Int. Students, vol. 8, no. 2, pp. 597–622, 2018, doi: 10.5281/zenodo.1249043.
[10]J. M. Collins, “Coming to America: Challenges for faculty coming to United States’ universities,” J. Geogr. High. Educ., vol. 32, no. 2, pp. 179–188, 2008, doi: 10.1080/03098260701731215.
[11]S. A. Smith, “Administration of extra-curricular activities in Montana high school,” vol. 1972, no. Spring, pp. 1–16, 1959.
[12]Q. She and T. Wotherspoon, “International student mobility and highly skilled migration: A comparative study of Canada, the United States, and the United Kingdom,” Springerplus, vol. 2, no. 1, pp. 1–14, 2013, doi: 10.1186/2193-1801-2-132.
[13]J. Baumert, O. Lüdtke, U. Trautwein, and M. Brunner, “Large-scale student assessment studies measure the results of processes of knowledge acquisition: Evidence in support of the distinction between intelligence and student achievement,” Educ. Res. Rev., vol. 4, no. 3, pp. 165–176, 2009, doi: 10.1016/j.edurev.2009.04.002.
[14]S. K. Baard, T. A. Rench, and S. W. J. Kozlowski, Performance Adaptation: A Theoretical Integration and Review, vol. 40, no. 1. 2014. doi: 10.1177/0149206313488210.
[15]I. Ognjanovic, D. Gasevic, and S. Dawson, “Using institutional data to predict student course selections in higher education,” Internet High. Educ., vol. 29, pp. 49–62, 2016, doi: 10.1016/j.iheduc.2015.12.002.
[16]J. Soland, “Combining Academic, Noncognitive, and College Knowledge Measures to Identify Students Not on Track For College: A Data-Driven Approach,” pp. 5–19, 2017.
[17]L. P. Zhuhadar and M. D. Lytras, “The Application of AutoML Techniques in Diabetes Diagnosis : Current Approaches , Performance , and Future Directions,” 2023.
[18]M. Al-kmali et al., “A Machine-Learning based Approach to Support Academic Decision-Making at Higher Educational Institutions,” no. Ml, 2020.
[19]A. Sid, A. Mohamed, and S. Ahmed, “Machine Learning for Strategic Decision Making during COVID-19 at Higher Education Institutes,” pp. 663–668, 2021.
[20]T. Cardona, E. A. Cudney, R. Hoerl, and J. Snyder, “Data Mining and Machine Learning Retention Models in Higher Education,” 2020, doi: 10.1177/1521025120964920.
[21]M. Nauman, “Guaranteeing Correctness of Machine Learning based Decision Making at Higher Educational Institutions,” IEEE Access, vol. PP, p. 1, 2021, doi: 10.1109/ACCESS.2021.3088901.
[22]S. Chen, R. N. Dnp, D. Voyles, and M. S. Rn, “HESI ADMISSION ASSESSMENT SCORES : PREDICTING STUDENT SUCCESS,” J. Prof. Nurs., vol. 29, no. 2, pp. S32–S37, 2013, doi: 10.1016/j.profnurs.2012.06.008.
[23]Z. A. Seal, W. Koek, and R. Sharma, “Correlation of Medical College Admission Test Scores and Self-assessment Materials with the United States Medical Licensing Examination Step 1 Performance,” 2020, doi: 10.7759/cureus.7519.
[24]A.-A. M. Dabaliz et al., “Predictive validity of pre-admission assessments on medical student performance,” Int. J. Med. Educ., vol. 8, pp. 408–413, 2017, doi: 10.5116/ijme.5a10.04e1.
[25]I. Basak and T. Saaty, “GROUP DECISION MAKING IN HIGHER EDUCATION USING THE ANALYTIC HIERARCHY PROCESS,” Math. Comput. Model., vol. 17, no. 4–5, pp. 101–109, 1993, doi: 10.1016/0895-7177(93)90179-3.
[26]G. W. Rigol, “ADMISSIONS DECISION - MAKING”.
[27]W. Ho, P. K. Dey, and H. E. Higson, “Multiple criteria decision-making techniques in higher education,” vol. 20, no. 5, pp. 319–337, 2006, doi: 10.1108/09513540610676403.
[28]A. Version, A data-driven approach to predict first-year students’ academic success in Higher Education Institutions, no. 351. 2021.
[29]A. L. Analysis, “THE PROMISE AND PERIL OF PREDICTIVE ANALYTICS IN HIGHER EDUCATION,” no. October, 2016.
[30]H. Erbay, “Use of machine learning techniques for the forecast of student achievement in higher education,” vol. 82, pp. 297–311, 2021, doi: 10.33407/itlt.v82i2.4178.
[31]D. Aggarwal, S. Mittal, and V. Bali, “Significance of Non-Academic Parameters for Predicting Student Performance Using Ensemble Learning Techniques,” vol. 10, no. 3, pp. 38–49, 2021, doi: 10.4018/IJSDA.2021070103.
[32]V. Kuleto, M. Ili, M. Dumangiu, M. Rankovi, and L. Mihoreanu, “Exploring Opportunities and Challenges of Artificial Intelligence and Machine Learning in Higher Education Institutions,” pp. 1–16, 2021.
[33]R. Using and M. Learning, “Exploring Opportunities and Challenges of Artificial Intelligence and Machine Learning in Higher Education Institutions,” pp. 1–17, 2020.
[34]N. Davidovitch and D. Soen, “Predicting Academic Success Using Admission Profiles,” vol. 11, no. 3, pp. 125–142, 2015.
[35]Bijoy, Md Hasan Imam, Anik Pramanik, Md Sadekur Rahman, Mehedi Hasan, Sumiya Alam Akhi, and Md Mahbubur Rahman. "MKRF stacking-voting: a data mining technique for predicting educational satisfaction level of Bangladeshis student during pandemic." In 2022 IEEE 7th International conference for Convergence in Technology (I2CT), pp. 1-7. IEEE, 2022.
[36]G. Ramponi, M. Brambilla, and R. Janssen, “T-CGAN : Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling,” pp. 1–12.
[37]J. A. Fessler, S. Member, and B. P. Sutton, “Nonuniform Fast Fourier Transforms Using Min-Max Interpolation,” vol. 51, no. 2, pp. 560–574, 2003.
[38]M. K. Dahouda and I. Joe, “A Deep-Learned Embedding Technique for Categorical Features Encoding,” IEEE Access, vol. 9, pp. 114381–114391, 2021, doi: 10.1109/ACCESS.2021.3104357.
[39]R. Blagus and L. Lusa, “SMOTE for high-dimensional class-imbalanced data,” 2013.