Call for Paper - January 2024 Edition
IJCA solicits original research papers for the January 2024 Edition. Last date of manuscript submission is December 20, 2023. Read More

UniPredict: A GRE-score based University Recommender System using Hybrid Model

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2021
Nishita Pali, Nikita Khivasara, Ashutosh Harkare

Nishita Pali, Nikita Khivasara and Ashutosh Harkare. UniPredict: A GRE-score based University Recommender System using Hybrid Model. International Journal of Computer Applications 183(24):43-48, September 2021. BibTeX

	author = {Nishita Pali and Nikita Khivasara and Ashutosh Harkare},
	title = {UniPredict: A GRE-score based University Recommender System using Hybrid Model},
	journal = {International Journal of Computer Applications},
	issue_date = {September 2021},
	volume = {183},
	number = {24},
	month = {Sep},
	year = {2021},
	issn = {0975-8887},
	pages = {43-48},
	numpages = {6},
	url = {},
	doi = {10.5120/ijca2021921622},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


In recent times, it is seen that many graduate students are willing to learn in foreign universities. Various factors like better opportunities of research, post-graduation, PhD and wider exposure to grab work in a plethora of jobs drive fresh graduates and experienced people to apply for different universities. This situation is predominant in students from Indian sub-continent and Asian countries. These students aim to get admissions in many top universities in the USA. According to the data obtained, the scores of exams like GRE, IELTS, TOEFL and, GPA of UG along with the work experience play a pivotal role in the university admissions. The aim of the web based recommendation system is to suggest the users - top 3 recommended colleges based on their profiles and inputs. As students spend huge amounts of money on counseling for obtaining university recommendations, our UniPredict system acts as a complete cost affordable platform for accurate results and user preferences. Collaborative filtering and content-based filtering is used to form a hybrid model that will be in turn used with ensemble learning to predict the universities. This system can be financially very affordable and helpful for the test takers to send 4 universities free applications after taking their test according to the GRE policy as of 2021.


  1. Ashutosh C. Harkare; Nishita Pali; Nikita Khivasara; Ishita Jain; Ravi Murumkar. “Personalized College Recommender - A System for graduate students based on different input parameters using hybrid model” - International Journal of Science and Research Technology, 2021.
  2. MahdiJalili, SajadAhmadian, MalihehIzad (2018) “Evaluating Collaborative Filtering Recommender Algorithms”: A Survey. In: IEEE Access 2018 date of publication November 28, 2018. Volume 6, 2018.
  3. Ling Huang, Chang-Dong Wand, Hong-Yang Chao, Jian-Huang Lai. “A Score Prediction Approach for Optional Course Recommendation via Cross-User-Domain Collaborative Filtering”. In. IEEE Access 2019 date of publication February 7, 2019. Volume 7, 2019.
  4. Priscila Valdiviezo-Diaz, Fernando Ortega, Eduardo Cobos, and Raúl Lara-cabrera “A Collaborative Filtering Approach Based on Naïve Bayes Classifier”. In. IEEE Access date of publication August 5, 2019. Volume 7, 2019.
  5. Farhan Ullah, Bofeng Zhang, Rehan Ullah Khan, Tae-Sun Chung, Muhammad Attique, Khalil Khan, Salim El Khediri, And Sadeeq J “Deep Edu: A Deep Neural Collaborative Filtering for Educational Services Recommendation”. In. IEEE Access 2020 date of publication June 15, 2020. Volume 8, 2020.
  6. Vidish Sharma, TarunTrehan, Rahul Chanana, Suma Dawn “StudieMe: College Recommendation System”. In 2019 3rd International Conference on Recent Developments in Control, Automation & Power Engineering (RDCAPE). 978-1-7281-2068-3/19/$31.00 ©2019 IEEE.
  7. Madhav Iyengar, Ayanava Sarkar, Shikhar Singh “A Collaborative Filtering based Model for Recommending Graduate Schools”. In IEEE Conference 2017. 978-1-5090-5454-1/17/$31.00 ©2017 IEEE.
  8. Dheeraj kumarBokde, Dheeraj kumarBokde, Debajyoti Mukhopadhyay “An Approach to A University Recommendation by Multi-Criteria Collaborative Filtering and Dimensionality Reduction Techniques”. In 2015 IEEE International Symposium on Nanoelectronic and Information Systems. 978-1-4673-9692-9/15 $31.00 © 2015 IEEE.
  9. Arta Iftikhar1, Mustansar Ali Ghazanfar1, MubbashirAyub, Zahid Mehmood And Muazzam Maqsood “An Improved Product Recommendation Method for Collaborative Filtering”. In IEEE Access 2020 date of publication June 30, 2020. Volume 8, 2020.
  10. Biao Cai, Yusheng Huang “Personalised recommendation algorithm based on covariance”. In. The 3rd Asian Conference on Artificial Intelligence Technology (ACAIT 2019). J. Eng., 2020, Vol. 2020 Iss. 13, pp. 577-583.
  11. Antonio Jesús Fernández-García, Roberto Rodríguez-Echeverría, Juan Carlos Preciado, José María Conejero Manzano, And Fernando  Sánchez-Figueroa “Creating a Recommender System to Support Higher Education Students in the Subject Enrollment Decision”. In. IEEE Access 2020 dateofpublicationOctober16,2020. Volume 8, 2020.
  12. NacimYanes, Ayman Mohamed Mostafa, (Member, IEEE), Mohamed Ezz,, And Saleh NaifAlmuayqil “A Machine Learning-Based Recommender System for Improving Students Learning Experiences”. In IEEE Access 2020 date of publication November 5, 2020. Volume 8, 2020.
  13. Dataset from: and


Model based collaborative filtering, Content based filtering, Pearson’s coefficient, Ensemble Learning, Neural Network Matrix factorization SVM, K-NN, Recommender systems, item-item, user-item, cosine similarity.