TY  - JOUR
AU  - Banik, Barnali Gupta
AU  - Syed, Aman Basha
PY  - 2026
DA  - 2026/03/07
TI  - Predicting University Admission Chances Using Machine Learning
JO  - Next-Generation Computing Systems and Technologies
T2  - Next-Generation Computing Systems and Technologies
JF  - Next-Generation Computing Systems and Technologies
VL  - 2
IS  - 1
SP  - 1
EP  - 9
DO  - 10.62762/NGCST.2026.766610
UR  - https://www.icck.org/article/abs/NGCST.2026.766610
KW  - prediction
KW  - admission
KW  - catBoost
KW  - historical data analysis
KW  - score-based forecasting
AB  - In the current academic landscape, students often face challenges in identifying suitable institutions for higher studies based on their academic and profile attributes. Existing advisory services and online tools are either expensive or lack predictive accuracy. This research proposes a machine learning-based admission prediction system that estimates the probability of university admission using historical applicant data. Linear Regression serves as a baseline model to capture linear relationships, Random Forest models non-linear feature interactions, and CatBoost is selected for its robustness on structured tabular data and native handling of categorical features. Comparative evaluation using MAE, RMSE, and R² shows that CatBoost outperforms the other models, achieving the lowest MAE of 0.042 and the highest R² of 0.81. The model also provides score-versus-admission probability analysis, enabling students to evaluate how improvements in test scores or CGPA affect their admission chances. The proposed approach offers an accurate, interpretable, and cost-free decision-support tool for students, addressing the limitations of existing admission prediction systems.
SN  - 3070-3328
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Banik2026Predicting,
  author = {Barnali Gupta Banik and Aman Basha Syed},
  title = {Predicting University Admission Chances Using Machine Learning},
  journal = {Next-Generation Computing Systems and Technologies},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {1-9},
  doi = {10.62762/NGCST.2026.766610},
  url = {https://www.icck.org/article/abs/NGCST.2026.766610},
  abstract = {In the current academic landscape, students often face challenges in identifying suitable institutions for higher studies based on their academic and profile attributes. Existing advisory services and online tools are either expensive or lack predictive accuracy. This research proposes a machine learning-based admission prediction system that estimates the probability of university admission using historical applicant data. Linear Regression serves as a baseline model to capture linear relationships, Random Forest models non-linear feature interactions, and CatBoost is selected for its robustness on structured tabular data and native handling of categorical features. Comparative evaluation using MAE, RMSE, and R² shows that CatBoost outperforms the other models, achieving the lowest MAE of 0.042 and the highest R² of 0.81. The model also provides score-versus-admission probability analysis, enabling students to evaluate how improvements in test scores or CGPA affect their admission chances. The proposed approach offers an accurate, interpretable, and cost-free decision-support tool for students, addressing the limitations of existing admission prediction systems.},
  keywords = {prediction, admission, catBoost, historical data analysis, score-based forecasting},
  issn = {3070-3328},
  publisher = {Institute of Central Computation and Knowledge}
}