AI-Based University Admission Prediction System Using Random Forest Regression

Abstract

Admission prediction plays a crucial role in assisting students to make informed decisions regarding higher education. This paper presents a machine learning–based admission prediction system that estimates the probability of admission for undergraduate (UG) and postgraduate (PG) programs. The proposed system utilizes academic performance, standardized test scores, and university rankings as input features. Separate datasets are maintained for UG and PG admissions, and a Random Forest Regression model is employed to predict admission chances. The system supports year-wise predictions, evaluates admission probability across multiple universities, and categorizes results into reach, match, and safety levels. Additionally, it provides profile improvement recommendations to enhance admission prospects. Experimental results demonstrate that the proposed approach offers an effective and user-friendly solution for admission guidance and decision support.

Introduction

The increasing competitiveness of university admissions has made it difficult for students to identify institutions that align with their academic profiles. Traditional counseling methods are often subjective and lack personalization, creating a need for intelligent, data-driven decision-support systems. Advances in machine learning enable predictive models to estimate admission probabilities using historical data and student performance metrics, reducing uncertainty in the admission process.

This paper proposes an AI-based University Admission Prediction System for both undergraduate (UG) and postgraduate (PG) programs using Random Forest Regression. The system predicts admission probability based on academic scores, entrance exams, qualitative factors (SOP, LOR, research experience), demographic considerations, and university rankings. It dynamically integrates ranking data from external sources and categorizes universities into Reach, Match, and Safety groups, offering clear guidance to applicants. Additionally, it provides personalized profile improvement suggestions to enhance admission chances.

The system architecture includes modules for dataset management, ranking integration, preprocessing, prediction, recommendation, and visualization. Experiments conducted on UG and PG datasets show effective performance, achieving a Root Mean Square Error (RMSE) of 6.8. Results demonstrate that entrance exam scores and university rankings are key factors influencing admission probability. Overall, the proposed system enhances transparency, personalization, and confidence in higher education decision-making for students and academic counselors.

Conclusion

This paper presented an AI-based University Admission Prediction System using Random Forest Regression. The system accurately predicts admission chances and assists students in selecting suitable universities. Experimental results validate the effectiveness of the proposed approach.

References

[1] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [2] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed., Springer, 2009. [3] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed., Morgan Kaufmann, 2012. [4] R. S. Baker and K. Yacef, “The State of Educational Data Mining in 2009: A Review and Future Visions,” Journal of Educational Data Mining, vol. 1, no. 1, pp. 3–17, 2009. [5] A. Peña-Ayala, “Educational Data Mining: A Survey and a Data Mining-Based Analysis of Recent Works,” Expert Systems with Applications, vol. 41, no. 4, pp. 1432–1462, 2014. [6] S. Kotsiantis, C. Pierrakeas, and P. Pintelas, “Predicting Students’ Performance in Distance Learning Using Machine Learning Techniques,” Applied Artificial Intelligence, vol. 18, no. 5, pp. 411–426, 2004. [7] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.

Copyright

Copyright © 2026 Kasturi Keerthana Reddy, Kotha Sai Teja, Vellore Ashrith Srinivasan, Zaheer , Mrs. G. Sneha. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.