Predicting Student Attrition in Competitive Programming: A Large-Scale Study Integrating Survey Insights and Global Behavioral Logs
DOI:
https://doi.org/10.53799/vka5w161Keywords:
Competitive Programming, Attrition Prediction, Educational Data Mining, Skill-Application Paradox, Early Warning System, Survey Analytics, Machine LearningAbstract
Competitive programming develops algorithmic reasoning in computer science students, yet sustained participation is fragile and many withdraw after stalled progress or thin mentorship. Dropout has been studied extensively in degree programs and online courses, but competitive programming attrition has not been examined as a behavioral phenomenon in its own right. This paper reports a two-layer study combining platform telemetry with a localized survey. We retrieved activity traces for 6,927 Codeforces accounts and reduced them to a balanced set of 1,816 users, half persistently active and half showing frustrated withdrawal, matched on peak rating so that disengagement is not confounded with skill. We additionally audit the features for temporal leakage, removing three columns whose predictive weight derives from when a user stopped rather than what they did. In parallel we surveyed students at ten universities in Bangladesh. Attrition follows an 83.7 percent fall in contest participation and a 42.7 percent drop in problems solved monthly. Students who stopped practised significantly less between contests while rating their own ability no lower than active peers, a divergence we term the Skill-Application Paradox. Random Forest reached a cross-validation F1 of 0.682 on the audited behavioral data and 0.832 on the survey layer.
References
[1] A. Laaksonen, Guide to Competitive Programming: Learning and Improving Algorithms Through Contests. Springer, 2017.
[2] S. S. Skiena and M. A. Revilla, Programming Challenges: The Programming Contest Training Manual. Springer, 2003. DOI: https://doi.org/10.1145/945526.945539
[3] S. Combefis and V. de le Vingne, “Learning programming and algorithm design through contest-like activities,” in Proc. WiPSCE, 2016, pp. 1–4.
[4] S. Halim and F. Halim, Competitive Programming 3: The New Lower Bound of Programming Contests. Lulu, 2013.
[5] L. Malmi, A. Korhonen, and R. Saikkonen, “Experiences in automatic assessment on mass courses and issues for designing virtual courses,” in Proc. ITiCSE, 2005, pp. 233–237.
[6] M. Guzdial, “Learner-centered design of computing education: Research on computing for everyone,” Synthesis Lectures on Human-Centered Informatics, vol. 8, no. 6, pp. 1–165, 2015. DOI: https://doi.org/10.1007/978-3-031-02216-6_1
[7] A. Robins, J. Rountree, and N. Rountree, “Learning and teaching programming: A review and discussion,” Comput. Sci. Educ., vol. 13, no. 2, pp. 137–172, 2003. DOI: https://doi.org/10.1076/csed.13.2.137.14200
[8] C. Romero and S. Ventura, “Educational data mining: A review of the state of the art,” IEEE Trans. Syst. Man Cybern. C, vol. 40, no. 6, pp. 601–618, 2010. DOI: https://doi.org/10.1109/TSMCC.2010.2053532
[9] S. B. Kotsiantis, “Supervised machine learning: A review of classification techniques,” Informatica, vol. 31, no. 3, pp. 249–268, 2007.
[10] P. Ihantola et al., “Educational data mining and learning analytics in programming: Systemic literature review and calls for action,” in Proc. Conf. ITiCSE Working Group Reports, 2015, pp. 41–63. DOI: https://doi.org/10.1145/2858796.2858798
[11] R. S. J. d. Baker and K. Yacef, “The state of educational data mining in 2009: A review and future visions,” J. Educ. Data Min., vol. 1, no. 1, pp. 3–17, 2009.
[12] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001. DOI: https://doi.org/10.1023/A:1010933404324
[13] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD, 2016, pp. 785–794. DOI: https://doi.org/10.1145/2939672.2939785
[14] G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” in Advances Neural Inf. Process. Syst., vol. 30, 2017, pp. 3146–3154.
[15] C. Watson, F. W. B. Li, and J. L. Godwin, “Predicting performance in an introductory programming course by logging and analyzing all code writing,” in Proc. ICET, 2013, pp. 319–324. DOI: https://doi.org/10.1109/ICALT.2013.99
[16] J. Sweller, “Cognitive load during problem solving: Effects on learning,” Cogn. Sci., vol. 12, no. 2, pp. 257–285, 1988. DOI: https://doi.org/10.1207/s15516709cog1202_4
[17] E. L. Deci and R. M. Ryan, Intrinsic Motivation and Self-Determination in Human Behavior. Springer, 1985. DOI: https://doi.org/10.1007/978-1-4899-2271-7
[18] A. Bandura, “Self-efficacy: Toward a unifying theory of behavioral change,” Psychol. Rev., vol. 84, no. 2, pp. 191–215, 1977. DOI: https://doi.org/10.1037/0033-295X.84.2.191
[19] Y. Miao and M. S. Ahmad, “Cross-disciplinary innovations in educational technology: Tracking burnout profiles in competitive programming environments,” Comput. Educ., vol. 192, p. 104651, 2023.
[20] M. A. Al-Razgan, H. S. Al-Khalifa, and A. S. Al-Salman, “Determinants of computer science student dropouts: A study utilizing ensemble voting models,” Comput. Hum. Behav., vol. 119, p. 106721, 2021.
[21] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
[22] P. Prinsloo and S. Slade, “Student vulnerability, agency, and learning analytics: An ethical framework,” J. Comput. High. Educ., vol. 28, no. 2, pp. 154–173, 2016.
[23] P. Blikstein, “Multimodal learning analytics,” in Proc. 3rd Int. Conf. Learning Analytics and Knowledge, 2013, pp. 102–106. DOI: https://doi.org/10.1145/2460296.2460316
Downloads
Published
Data Availability Statement
The Codeforces behavioral data were collected via the public Codeforces API and are available from the corresponding author upon reasonable request. The survey dataset contains anonymized responses from student participants across 10 Bangladeshi universities and is available from the corresponding author upon reasonable request, subject to participant privacy and institutional considerations.
Issue
Section
License
Copyright (c) 2026 AIUB Journal of Science and Engineering (AJSE)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
AJSE contents are under the terms of the Creative Commons Attribution License. This permits anyone to copy, distribute, transmit and adapt the work non-commercially provided the original work and source is appropriately cited.
