e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:03/March-2023 Impact Factor- 7.868 www.irjmets.com

COLLEGE RECOMMENDATION SYSTEM USING ARTIFICIAL INTELLIGENCE

AND MACHINE LEARNING
Prof. Sunil Sonawane*1, Miss. Madhavi Gosavi*2, Miss. Aparna Pawar*3,
Mr. Omkar Pawar*4, Mr. Dhananjay Dighe*5
*1Professor, Department Of Technology, AISSMS's Polytechnic, Pune, Maharashtra, India.
*2,3,4,5Student, Department Of Information Technology, AISSMS's Polytechnic,
Pune, Maharashtra, India.
ABSTRACT
A student's decision to enroll in a particular educational institution is one of their most important or important
choices because it is essential to their career development and growth. The educational sector's engineering
sector is one of the fastest growing. The engineering sector is quite competitive for students throughout India.
The topic that is now being debated a lot in India is college rankings. Every student must make a significant
decision when selecting their educational institution because it affects how their personality and career will
grow. This project lets students learn everything they need to know about engineering colleges. Some
numerous websites and apps provide details about different engineering colleges, however, when it comes to
students, they must get specific details about factors like professors, campus life, hostel amenities, placement,
etc. Today, CET or diploma final year scores are one of the key requirements for admission to any engineering
college. Students from small towns and cities are less likely to attend different colleges. The fresh talent will be
adequately channeled as per their interests if these pupils have enough exposure. The user will assess the
questions based on his level of interest. The dataset will contain the list of colleges so that the accuracy and
precision of the system can be determined.
Keywords: College, Dataset, Education, Engineering, Interest, Recommendation.
I. INTRODUCTION
Humans employ numerous methods in our computer era for various purposes. There are numerous software
programs and human applications available. Using this software, we may create a list of colleges a student is
qualified to attend. We put forth a system to offer a recommendation system that will produce a list of colleges
the user is interested in. This will be accomplished by asking a few questions about the college, such as about its
facilities, campus life, employment opportunities, athletics, and extracurricular activities. The user will assess
the questions based on his level of interest. This project's difficult task is compiling a database of every
engineering institution in Maharashtra and generating a list of colleges based on user preference. The system
would produce a list of colleges for students who have completed their HSC and Diploma in any engineering
discipline after selecting their grades and other criteria. Many students from throughout Maharashtra complete
their HSC and diploma exams each year. Every student desires to enroll in the best engineering colleges after
clearing their examinations. Every student must apply to a certain minimum number of colleges where he or
she might be admitted as part of the admissions process. A list of the colleges to which they desire to get
admitted must therefore be made by a candidate. The list-making process requires a significant amount of
manual college study. The college list will be generated automatically by our system. We aim to decrease this
difference by creating a system that would produce a list of colleges for which a candidate is qualified.
II. LITERATURE SURVEY
In this paper [1], user-based collaborative filtering and association rule features are considered for selecting
the highly rated top-N books. They have combined the features of classification, user-based collaborative
filtering, and association rule mining for recommending books to buyers. The main motive of the paper was to
develop the technique which recommends the most suitable books to the students according to the price range
and author.
In this paper [2], they used data mining and machine learning techniques. This paper issues the problem faced
by the students who have completed their SSC examination from the various boards to select the stream and

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[25]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:03/March-2023 Impact Factor- 7.868 www.irjmets.com
college. In this paper, they have focused on how to make the process of junior college admission more
convenient and help students to choose colleges that fit best for them based on their needs. They have used
various data mining and query optimization techniques for the college recommendation process. For more
accuracy or optimality in recommendations, they have also used Naive Bayesian and Decision trees algorithms
which help in minimizing the search time of colleges and the system will be able to give optimized results.
In this paper [3], they presented a model to generate recommendations based on the marks of students. It
offers better opportunities in the project development cycle under the requirement phase and design phase.
The social media and Ecommerce market has tapped into the recommender system to boost its growth by
providing precise results. They mentioned that, provide either service or product recommendations using the
information gathered in the software engineering process. It is broadly divided into three categories which are
Collaborative, Content-based, and Hybrid recommendation approaches.
In this paper [4], they present a novel web platform for a college selection process. Having a recommendation
system as a helping hand to give them detailed information about the options they have and the best options to
choose from according to their caliber is a huge requirement. In this paper, we worked on designing a
recommendation system that could understand a user’s skill set and interest through the data from the User’s
Profile to suggest recommended options of colleges for the users to select. We have developed the college
recommendation system as a web platform that gives the result as top matched colleges for a particular use.
In this paper [6], they mentioned the lack of semantic factors in recommendation systems and describes the
different recommendation techniques that are being employed in the current e-commerce website.
Recommendation systems can be broadly classified into three categories: content-based, collaborative, and
hybrid recommendation approaches. Content-based systems consider the properties of the items to be
recommended. For instance, if an Amazon user has purchased many romantic novels, then the content-based
recommendation system recommends novels in the database as having the “romantic” genre. Collaborative
filtering systems recommend items based on similarity measures between like-minded users and/or items. The
items recommended to a user are those preferred by similar users. This paper also emphasizes the need for
semantics in the current recommendation system.
In this paper [7], they have used the following approaches – a simple recommendation system, a content-based
filtering approach, collaborative-based filtering approach., with the huge number of technologies and a
tremendous amount of information being available at the disposal over the Internet, a huge amount of data is
made available to users. This results in a condition known as “information overload”. Due to these, it is difficult
for a person to search and access information for taking decisions to arrive at an effective conclusion. To
perorate this nut, there are filtering systems for information, known as the recommendation system or
recommendation engine, considered here in the paper, that help a person in identifying significant and possible
services or products of interest based on the preferences given by him/her. This results in searching through
lots of results to find the one that the user needs.
In this paper [8], they used data mining techniques. They have proposed a system that provides a
recommendation system that generates the user-interested college’s list. The database is collected by asking a
few questions related to the college like college infrastructure, campus life, placement, sports, and cultural
activities. The list of colleges is stored in the dataset for calculating the accuracy and precision of the system.
This paper [9], —This paper presents a new System designing method for job recommendation of College
Graduates based on Hadoop in China. With the enlargement of the scale of Chinese graduates and the
improvement of the employment demand of enterprises, the employment situation of college graduates is
becoming more and more serious. College graduates can't get a satisfactory job, while enterprises can't recruit
suitable graduates. To improve the satisfaction and efficiency of college graduates’ employment and enterprise
recruitment, an intelligent employment recommendation system was designed in this paper which was based
on the collaborative filtering recommendation framework Mahout. With the system, the intelligent
recommendation mechanism of schools, enterprises, and graduates could be realized, and the employment
efficiency, the satisfaction of college graduates, and the efficiency of recruiting enterprises could be effectively
improved.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[26]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:03/March-2023 Impact Factor- 7.868 www.irjmets.com
In this paper [10], they had given a systematic review of the recommendation System. In the paper, they
described the challenges developers faced while proposing any recommendation system. As per them, the key
challenges to a recommendation system arises due to the huge growth of data on the internet as well as the no
of users visiting the websites. In this paper, they have explained approximately the recommendation system, its
processes, and the technology used. Their study shows that an item-based recommendation system is an
efficient recent method to make recommendations where users could provide the whole documents instead of
just keywords and make internal and external ratings to make a recommendation system.
In this paper [11], they reviewed data mining based on recommendation Methods. They have described the
recommendation system techniques such as content-based recommendations, collaborative recommendations,
Information based suggestions, and hybrid recommender systems. As they say, the most used recommendation
method is the web-based approach used for recommending the set of ranked and limited products from all
available products of the same category without using direct inputs from end users. In this paper, they have
presented the systematic review of a novel fuzzy preference graph-based B2B marketing campaign
recommendation system to address the challenges of the complex and dynamic nature of the business buying
process. The fuzzy approach is used to address the challenges of vague or fuzzy online users’ preferences
problem.
In this paper [12], they designed and implemented a Recommendation system for college libraries. They
mentioned that to meet the real-world circulation demands for college library books, in-depth analysis is
performed on the library book circulation data and readers' preferences. The Apriori algorithm is used to build
the recommendation for college libraries. The proposed system was able to provide efficient and custom
services, enabling readers to find the books of their interest more quickly.
In this paper [13], they described the various web recommender systems in use by some popular websites on
the internet like Amazon.com, LinkedIn.com, YouTube.com, etc. Further, we have described the various
approaches used in the various recommender systems such as Content-based, Collaborative, and Hybrid
recommender systems. At the end of this paper, they focused on some of the main challenges faced by web
recommender systems and analyze some techniques to overcome them.
III. PROBLEM STATEMENT
For a student who wants to be admitted to a top engineering college, finding a respectable institution to attend
is a difficult task. Students search from a variety of perspectives, including the college campus, the faculty,
extracurricular activities, placements, etc. According to the student's grades and other selected criteria, the
College Recommendation System will produce a list of colleges. It will chop out details and lessen manual
research in engineering colleges.
IV. PROPOSED METHODOLOGY

Fig. 1

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[27]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:03/March-2023 Impact Factor- 7.868 www.irjmets.com
The proposed system will be the website developed using HTML, CSS, and JavaScript mainly where we will
implement our recommendation system. The recommendation mainly uses the python language. To store the
database of the engineering college we are using MySQL. The system will first store the information provided
by the user or student and then it will match the data with the college database and display the list of colleges
according to the match.
A. Step-1: Survey to collect college data:
The recommendation system mainly works on the database. The database is the root of any recommender
system. To recommend the colleges to the users according to their choice it is necessary to have sufficient data
on the colleges for accurate results. We will collect the data of colleges from the students of that colleges, from
the students who have passed out, use some internet resources, etc.
Step-2: Creating Modules
As our system is currently proposed for the students who are appearing for B. E (1 st year Engineering) and DSE
(Direct second-year engineering). The main parameters of the system are marks, branches, distance, and
campus infrastructures.
Marks:
Students who need to take admitted to B.E and DSE need to enter their HSC, CET marks, and Diploma Final Year
Marks Respectively.
Branch:
As we know, engineering is a sector in which there are several branches where students can enhance their
knowledge in their interested branches. Users in the system can select one or more branches.
Distance:
The distance can be the major parameter to choose any institute. Users need to decide how much distance
he/she can travel every day. Users need to provide their location and the distance he/she can travel.
Campus Infrastructure:
This includes campus placements, extra curriculum activities, Co-curriculum activities, campus life, and other
some parameters.

Fig. 2
Step-3: Retrieving data and Displaying list:
The data of the colleges stored and the data entered by the user are matched together and using some
recommendation algorithm the list of colleges will be displayed to the user. This list will reduce the manual
research of the college and cutoff details.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[28]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:03/March-2023 Impact Factor- 7.868 www.irjmets.com

Fig. 3
V. PROJECT PURPOSE
The topic that is now being debated a lot in India is college rankings. Every student must make a significant
decision when selecting their educational institution because it affects how their personality and career will
grow. This project lets students learn everything they need to know about engineering colleges. Some
numerous websites and apps provide information on different engineering colleges, but when it comes to
students, they must gain specific insights into aspects like faculty, campus life, hostel facilities, placement, etc.
Today, CET or diploma final year scores are one of the key requirements for admission to any engineering
college.
VI. FUTURE ENHANCEMENT
Many youngsters will benefit from our system because there isn't one like it yet. Our system will currently only
be accessible to applicants for B.E. programs, and second-year direct engineering students will be the only ones
who can use and gain from it. They can discover about engineering colleges easily and swiftly.
VII. CONCLUSION
Thus, in this paper, we have focused on how to make the process of B.E and Direct second year admission more
convenient and help students to choose colleges that fit best for them and based on their needs. To make
college recommendations, we have applied a variety of data mining and query optimization approaches. We are
proposing this system, to reduce the manual research of engineering colleges and cut off details.
ACKNOWLEDGEMENT
I would like to express my deep gratitude to Professor Mr. S.S. Sonawane, our project guide, for their patient
guidance, enthusiastic encouragement, and useful critiques of this research work.
I would also like to thank Mrs. V.R. Palandurkar, for her advice and assistance in keeping our progress on
schedule.
I would also like to extend my thanks to the technicians of the laboratory of the Information Technology
department for their help in offering me the resources in running the program.
Finally, I wish to thank my parents for their support and encouragement throughout my study.
VIII. REFERENCES
[1] S. Tewari, A. Kumar and A. G. Barman, "Book recommendation system based on combine features of
content-based filtering, collaborative filtering and association rule mining," 2014 IEEE International
Advance Computing Conference (IACC), 2014, pp. 500-503, doi: 10.1109/IAdCC.2014.6779375.
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[29]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:03/March-2023 Impact Factor- 7.868 www.irjmets.com
[2] Vinit Jain, Mohak Gupta, Jenish Kevadia, Prof. Krishnanjali Shinde, 2017, College Recommendation
System, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) ICIATE –
2017 (Volume 5 – Issue 01).
[3] N. Karbhari, A. Deshmukh and V. D. Shinde, "Recommendation system using content filtering: A case
study for college campus placement," 2017 International Conference on Energy, Communication, Data
Analytics and Soft Computing (ICECDS), 2017, pp. 963-965, doi: 10.1109/ICECDS.2017.8389579.
[4] V. Sharma, T. Trehan, R. Chanana and S. Dawn, "StudieMe: College Recommendation System," 2019 3rd
International Conference on Recent Developments in Control, Automation & Power Engineering
(RDCAPE), 2019, pp. 227-232, doi: 10.1109/RDCAPE47089.2019.8979030.
[5] Z. Wang, A. Maalla and M. Liang, "Research on E-Commerce Personalized Recommendation System
based on Big Data Technology," 2021 IEEE 2nd International Conference on Information Technology,
Big Data and Artificial Intelligence (ICIBA), 2021, pp. 909-913,
doi: 10.1109/ICIBA52610.2021.9687955.
[6] S. Shaikh, S. Rathi and P. Janrao, "Recommendation System in E-Commerce Websites: A Graph Based
Approached," 2017 IEEE 7th International Advance Computing Conference (IACC), 2017, pp. 931-934,
doi: 10.1109/IACC.2017.0189.
[7] S. Roy, M. Sharma and S. K. Singh, "Movie Recommendation System Using Semi-Supervised
Learning," 2019 Global Conference for Advancement in Technology (GCAT), 2019, pp. 1-5,
doi: 10.1109/GCAT47503.2019.8978353.
[8] V. Powar, S. Girase, D. Mukhopadhyay, A. Jadhav, S. Khude and S. Mandlik, "Analysing recommendation
of colleges for students using data mining techniques," 2017 International Conference on Advances in
Computing, Communication and Control (ICAC3), 2017, pp. 1-5, doi: 10.1109/ICAC3.2017.8318781.
[9] Z. Chen, W. Liang, X. Gao, Z. Zhou and M. Wu, "Research on the Accurate Recommendation Management
System for Employment of College Graduates on Hadoop," 2019 5th International Conference on Big
Data and Information Analytics (BigDIA), 2019, pp. 19-22, doi: 10.1109/BigDIA.2019.8802855.
[10] A. Khan, A. Yadav, A. Chand Rahi and J. Sinha, "Systematic Review on Recommendation Systems," 2020
2nd International Conference on Advances in Computing, Communication Control and Networking
(ICACCCN), 2020, pp. 952-956, doi: 10.1109/ICACCCN51052.2020.9362888.
[11] S. A. Patil and P. Agarkar, "Systematic Review of Data Mining based Recommendation Methods
Reference to Business to Business (B2B) Recommendation," 2019 5th International Conference On
Computing, Communication, Control And Automation (ICCUBEA), 2019, pp. 1-7,
doi: 10.1109/ICCUBEA47591.2019.9128551.
[12] W. Xueyuan and Y. Bo, "Design and Implementation of an Apriori-Based Recommendation System for
College Libraries," 2018 International Conference on Engineering Simulation and Intelligent Control
(ESAIC), 2018, pp. 372-375, doi: 10.1109/ESAIC.2018.00094.
[13] S. Jain, A. Grover, P. S. Thakur and S. K. Choudhary, "Trends, problems and solutions of recommender
system," International Conference on Computing, Communication & Automation, Greater Noida, India,
2015, pp. 955-958, doi: 10.1109/CCAA.2015.7148534.
[14] A. Al-Doulat, "Surprise and Curiosity in A Recommender System," 2018 IEEE/ACS 15th International
Conference on Computer Systems and Applications (AICCSA), Aqaba, Jordan, 2018, pp. 1-2, doi:
10.1109/AICCSA.2018.8612897.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[30]