TRIBHUVAN UNVERSITY

Institute of science and technology

Final year project report

On

"Job Recommendation System"

Submitted to

Department of computer science and information technology

Nepalaya college

In partial fulfillment of the requirement for the bachelor’s degree in computer science and
information technology

Submitted By

Madhu Gaire(11002/073)

Nabina Pathak(11005/073)

Samjhana Karki(11017/073)

Sumitra Ghimire(7517/072)

1|Page
 SUPERVISOR’S RECOMMENDATION

I hereby recommend that this project prepared under my supervision by Madhu

Gaire(11002/073) Nabina Pathak(11005/073) Samjhana Karki(11017/073) Sumitra
Ghimire(7517/072) entitled "Job Recommendation System" in partial fulfillment of the
requirements for the degree in Computer Science and information technology be for the
evaluation.

______________________

Mr.Bhupi Saud

Project supervisor

2|Page
 CERTIFICATE OF APPROVAL

This is to certify that this project prepared by Madhu Gaire(11002/073), Nabina

Pathak(11005/073), Samjhana Karki(11017/073), Sumitra Ghimire(7517/072) entitled
“Job Recommendation System” in partial fulfillment of the requirements for the degree
B.Sc.in Computer science and information Technology has been well studied. In our opinion
it is satisfactory in the scope and quality as a project for the required degree.

______________________ __________________

Mr.Bhupi Saud Mr.prasant Gautam

Supervisor Coordinator

Department of BSC CSIT Department of CSIT

Nepalaya College Nepalaya College

Kalanki, Kathmandu Kalanki, Kathmandu

_____________________ _________________

External Examiner (Internal Examiner)

Central Department of CSIT Central Department of CSIT

Tribhuvan University Tribhuvan University

Kirtipur, Nepal Kirtipur, Nepal

3|Page
 ACKNOWLEDGEMENT

We would like to take the opportunity to express our sincere thanks to our project Supervisor
Mr.Bhupi Saud for the individual support and guidance throughout our project research
work. Without his kind guidance and support this was not possible.

We would also like to thank Mr. Prashant Gautam. Coordinator of CSIT Department for
his encouragement and feedback which helped us to track and schedule the process
effectively.

We also extend our sincere thanks to all the faculty members and the non-teaching staff for
creating best environment to carry out project smoothly.

4|Page
 Abstract
In today's world there are many jobs seeking and recruitment websites, we provide an
enhanced system which is a user-friendly recommender system. The website will be designed
for various interactions between the user and system.

It provides organized resources the user needs to express their interests. The system exploits
the jobs and user profiles. The system uses the cosine similarity algorithm for
recommendations of jobs. The vacancies collected from the companies and job search by job
seeker are used in order to recommend to job seeker using algorithm like cosine similarity.

As companies provide the system their requirement for specific job in order of which system
recommend the job because meanwhile job seeker also provide their skills which is the keys
point of our system. We used skills as the matching point of our system in order to
recommend the job to the job seeker.

5|Page
 Table of Contents
Abstract......................................................................................................................................5

Chapter 1..................................................................................................................................10

Introduction..............................................................................................................................10

1.1. Job Recommendation System...................................................................................10

1.2. Problem Definition....................................................................................................10

1.3. Objectives..................................................................................................................11

1.4. Scope and Limitation................................................................................................11

Chapter 2..................................................................................................................................12

Requirement Analysis and Feasibility Analysis......................................................................12

2.1. Related Work................................................................................................................12

2.2. Related Technology......................................................................................................13

2.3. Requirement Analysis...................................................................................................14

2.3.1. Functional Requirements.......................................................................................14

2.3.2. Non-Functional Requirements...............................................................................15

2.4. Feasibility Analysis.......................................................................................................15

2.4.1. Economic Feasibility.............................................................................................15

2.4.2. Technical Feasibility..............................................................................................16

2.4.3. Operational Feasibility...........................................................................................16

2.5. Structuring System Requirements.................................................................................17

2.5.1. Data Modeling.......................................................................................................17

2.5.2. Process Modeling...................................................................................................18

Chapter 3..................................................................................................................................20

System Design.........................................................................................................................20

3.1. System Design...........................................................................................................20

6|Page
 3.1.1. Schema Design..................................................................................................21

3.1.2. Input output design............................................................................................22

3.1.3. Process Design...................................................................................................23

Chapter4...................................................................................................................................24

Implementation and Testing....................................................................................................24

4.1. Implementation.............................................................................................................24

4.2. Tools Used...................................................................................................................25

4.2.1. Analysis and Design Tools....................................................................................25

4.2.2. Implementation Tools............................................................................................25

4.2.3. Others Tools and Platforms...................................................................................25

4.2.4. Algorithm...............................................................................................................26

4.3. Testing...........................................................................................................................27

4.3.1. Unit Testing...........................................................................................................27

4.3.2. Integration Testing.................................................................................................28

4.3.3. System Testing.......................................................................................................28

Chapter 5..................................................................................................................................30

Maintenance and Support........................................................................................................30

5.1. Results...........................................................................................................................30

5.2. Maintenance and Support..............................................................................................30

Chapter 6..................................................................................................................................31

Conclusion and Recommendation...........................................................................................31

6.1. Conclusion....................................................................................................................31

6.2. Future Enhancement.....................................................................................................31

REFERENCES........................................................................................................................32

Appendices..............................................................................................................................33

7|Page
List of Figures:
Figure 1: Use Case Diagram....................................................................................................15
Figure 2: ER Diagram..............................................................................................................17
Figure 3:Context DFD of Job Recommendation System.......................................................18
Figure 4:Level0, Level1, Level2 DFD of Job Recommendation System................................19
Figure 5: System Architecture of Job Recommendation System............................................20
Figure 6: Schema Diagram of Job Recommendation System.................................................21
Figure 7: Input Output System of Job Recommendation System............................................22
Figure 8: Flowchart of job recommendation system...............................................................23
Figure 9: Workflow of Content Based System........................................................................25
Figure 10: Home Page.............................................................................................................33
Figure 11: Admin Panel...........................................................................................................34
Figure 12:Registration Form for Company.............................................................................35
Figure 13: Form to post vacancy.............................................................................................36
Figure 14:Registration Form for User.....................................................................................37
Figure 15:Recommended job to the User................................................................................38
Figure 16: Login Page for Admin............................................................................................39
Figure 17:Algorithm Used.......................................................................................................40

8|Page
List of Tables
Table 1: Unit Testing...............................................................................................................28
Table 2: Integration Testing.....................................................................................................28
Table 3: System Testing..........................................................................................................29

9|Page
 Chapter 1

Introduction

1.1. Job Recommendation System

Recommendation systems are tools that use various techniques and algorithms to isolate
irrelevant information from a huge amount of data and generate personalized suggestions of a
small subset of them which a user can examine in a reasonable amount of time.
Recommender system is one application plug-in that is being used by many vectors and
online service providers to understand the needs of online users. Based on their need, the
system is able to suggest them the best suitable product or match.

Job recommendation system is the web portal which helps user to find the job as s/he
searched or visited in the past. This system provides platform for both company and job
searcher for seeking and recruiting job.

Sites providing support to the former case are more popular and have a simpler structure;
however, their recommendations are less accurate than those of the sites using profile data.
Job recommendation sites implemented a variety of types of recommender systems, such as
content-based filtering, collaborative filtering, knowledge-based and hybrid approaches.

1.2. Problem Definition

Due to a large growth of online data in recent years, the task of extracting the relevant
information has become a tedious process for the recruitment industry. This industry is
heavily dependent upon accurately estimable information filtering systems. Due to this data
boost, job listings and recruitment service websites have experienced a dip in quality and
performance. In the current scenario, both job seekers and recruiters have to undergo a huge
pool of job descriptions and job listings information in order to come up with final short
listings. On the other end, this process is completely manual due to which there are high
chances of missing out of the appropriate and suitable job or candidate, plus it is also a time-
consuming process.

10 | P a g e
1.3. Objectives
The main objective of our project is to provide a service to the job seeker and make them
possible in their work.

• To demonstrate and find out the available job according to user needs.

• To help companies find employees with the required skill and qualification

1.4. Scope and Limitation

Scope

Using a recommendation’s functionality in the business system it will benefits both

the customers and the service provider or business owner. Users become more
engaged in the websites when they find the item recommended for them of their
interests. Due to the more engagement of users, service provider also gets an
opportunity to grow their business broadly.

Limitation

Our system will not be able to recommend the job as per the user interest. As user
provide their skill as per that our system will recommend the job but our system will
not be able to recommend as per their education qualifications. But we will try our
best to overcome from this limitation.

11 | P a g e
 Chapter 2

Requirement Analysis and Feasibility Analysis

2.1. Related Work
The root of content-based filtering is in information retrieval and information filtering
research. As we said earlier, content-based recommender systems suggest items similar to
those that a user has previously liked. In other words, different candidate items are compared
with items that were rated by the user in the past and the best-matching items are
recommended. In [1] they present an implicit news recommender system with the capability
of integrating multiple modes, like radio-television channels, websites, and other kind of
media like written text and spoken words. Di Massa et. al. [1] used natural language
processing techniques like TF*IDF to extract users' interests from their RSS blogs. Then the
relationship between those interests and both online newspaper articles and broadcast news
stories is found using semantic analysis. Di Massa et. al.'s [1] recommender system is a
combination of content-based filtering and collaborative filtering. In content-based filtering,
the TF*IDF technique was used to define their keywords and then and jobs keywords that
match the user interests, using a similarity function. They also and the similarity among users
employing collaborative filtering.

Recently, Job Recommendation System (JRS) have started to play an important role on the
recruiting process, especially on online recruiting websites. Salton et al suggested a CB JRS
that utilizes the Vector Space Model (VSM) [ [2]. In VSM, each job was represented by a
vector in an n-dimensional space, where each dimension corresponded to a textual feature
from the overall feature-set of the job set. Furthermore, each job was represented as a vector
of feature weights, where each weight designated the degree of association between the
feature and the job. Finally, a relevance score is computed for a candidate employee and each
candidate job and then a list of top-k jobs with the highest score are suggested.

In the work of [3], “we suggested a content-based job recommendation algorithm that deals
with the recommendation of candidates for a specific job position. In proportion with the
problem definition of our current approach, a specific job position was described by several
required qualifications with specific values and a number of candidates had respective values

12 | P a g e
for each of these qualifications. The job applicant with the closer or even higher of the
respective values of the specific job requirements had higher probability to be recruited. Our
algorithm utilized Euclidean distance to perform a primary analysis in order to investigate
how the job seeking and recruiting field could have benefited further. More specifically, our
algorithm aimed at quantifying the suitability of a candidate employee for a specific job
position”.

2.2. Related Technology

Nowadays, job search is a task commonly done on the Internet using job search engine sites
like LinkedIn1, Indeed2, and others. Commonly, a job seeker has two ways to search a job
using these sites:

1) Doing a query based on keywords related to the job vacancy that he/she is looking for

2) Creating and/or updating a professional profile containing data related to his/her

education, professional experience, professional skills and other, and receive personalized
job recommendations based on this data.

Some of the related technologies are:

1. LinkedIn
This site uses advanced search option to refine your search on the basis of keyword,
country and zip code. You can also save job searches, and even receive emails about
new job listings. User can get access to what they want based on their job
qualification.
2. Indeed
Job listings from thousands of sources across the internet, including job boards,
company career sites and recruiter listings. This consolidation of job listings both
eliminates the need for companies to post jobs in multiple locations and streamlines
the search process for job seekers. Jobs posted directly to Indeed are managed
through an online employer dashboard and can be easily browsed and applied to from
mobile devices.
3. Jobs Nepal

13 | P a g e
 Jobsnepal.com is a common platform for both Job Seekers and Employers. If you
register/sign up as a job seeker then you can write and save multiple resumes, search
open vacancies posted at JobsNepal.com, see the profiles of the companies who are
registered, apply for a job online, and be notified via e-mail when any job that
matches your criteria is posted. As an employer registered at JobsNepal.com, you can
not only keep your company profile but post Normal Jobs / Hot Jobs vacancies at
your company, search resumes/CV, view profiles of other employers and more.

2.3. Requirement Analysis

To design a system, at first, we should know the requirement of the system i.e., we are
planning to design job recommendation system and our requirement can be show the job
vacancy as per the search, user friendly, don’t show to the job holder, and so on.

We are planning to collect the requirement visiting to different companies and knowing their
idea to search for the staffs.

2.3.1. Functional Requirements

Functional requirements identify the provision of the system and the system’s reaction to the
certain output and how the system should behave in day-to-day basis. This system is focused
on skill of user, skill required for company and recommend the job to user.

The functional requirements of “job recommendation system” includes the following tasks: -

• System should take skill of user and compare with the skill required for companies.
• System should not take long to recommend the job to the users.
• System should recommend the job correctly to the user.
• The result must be display to the user after computation.

14 | P a g e
 Figure 1: Use Case Diagram

2.3.2. Non-Functional Requirements

 Usability: The system needs to be usable by every user.
 Maintenance: The system needs to be maintainable.
 Extendable and Scalability: The system is extendable and scalable for future
enhancements.

2.4. Feasibility Analysis

2.4.1. Economic Feasibility
The purpose of economic feasibility assessment is to determine the positive economic
benefits to the organization that proposed system will provide. It includes quantification and
identification of all the benefits expected. This assessment typically involves a cost/benefit
analysis. The probable cost at the first step of the project includes all the hardware and

15 | P a g e
software costs, which are minimal for our project. As we are using only laptop and desktop
and for data collection too, we are using dome data, which makes low cost to design the
system.

2.4.2. Technical Feasibility

This project is based on an outline design of system requirements to determine whether the
company/team has the technical expertise to handle completion of the project. It is an
evaluation of the hardware and software and how it meets the need of proposed system.

We are making web base application by using only our laptop or desktop. Simple code and
algorithm are used in order to design the system.

2.4.3. Operational Feasibility

Operational Feasibility is the measure of how a proposed system solves a problem and takes
advantages of the opportunities identified during scope definitions and how it satisfies the
requirements identified in the requirement analysis phase of the project development. To
ensure success, desired operational outcomes must be imparted during design and
development. These include such design-dependent parameters such as reliability,
maintainability, usability, productivity, sustainability and others.

As we know there is lots of gab between company and the job searcher and we are building
such system which will break this gab. I guess this will somehow decrease the
unemployment problem too.

16 | P a g e
2.5. Structuring System Requirements

2.5.1. Data Modeling

Figure 2: ER Diagram

17 | P a g e
2.5.2. Process Modeling

Figure 3:Context DFD of Job Recommendation System

18 | P a g e
Figure 4:Level0, Level1, Level2 DFD of Job Recommendation System

19 | P a g e
 Chapter 3

System Design
3.1. System Design
In Job Recommendation System user means job seekers whom have to fill up the form in
order to get job recommendation. As there is company registration form too from where
company is able to post the vacancies available.

Skill is key points for our system as both company and user provide skill to the system which
is the similarity between user and vacancy available. As we are using cosine similarity
algorithm and here similarity is skill analyzing of which our system recommends the job to
the users.

Figure 5: System Architecture of Job Recommendation System

20 | P a g e
3.1.1. Schema Design

Figure 6: Schema Diagram of Job Recommendation System

21 | P a g e
 3.1.2. Input output design
In input output design, both user and company have to fill up registration form as input
where user and company have to provide many information along with skill user have and
skill required for specific job. With the help of data provided by both user and company we
have use cosine similarity algorithm which analysis the skill as skill is only the similar entity
in both company and user profile, then our system recommends the job as an output to the
users.

Figure 7: Input Output System of Job Recommendation System

22 | P a g e
3.1.3. Process Design

Figure 8: Flowchart of job recommendation system

23 | P a g e
 Chapter4

Implementation and Testing

4.1. Implementation
Content Based System

Content-based technique[4] is a domain-dependent algorithm and emphasizes more on the

analysis of the attribute s of items in order to generate predictions. When documents such as
web pages, publications and news are to be recommended, content-based filtering technique
is the most successful. In content-based filtering technique, recommendation is extracted
from the content of the items the user has evaluated in the past. Items that are mostly related
to the positively rated items are recommended to the user. CBF uses different types of
models to find similarity between documents in order to generate meaningful
recommendations. These techniques make recommendations by learning the underlying
model with either statistical analysis or machine learning techniques. Content-based filtering
technique does not need the profile of other users since they do not influence
recommendation. Also, if the user profile changes, CBF technique still has the potential to
adjust its recommendations within a very short period of time. The major disadvantage of
this technique is the need to have an in-depth knowledge and description of the features of
the items in the profile made based on the user profiles using features.

As we mention before there different fields to recommend job with in CBF, among them we
are using skill (provided by job seeker and company) in order to find jobs. There are different
types of algorithm in CBF[5] among them we are using Cosine similarity algorithm.

Cosine similarity is a measure of similarity between two non-zero vectors of an inner product
space. The cosine of two non-zero vectors can be derived by using the Euclidean dot product
formula:

A.B = ||A||||B||cosØ

Given two vectors of attributes, A and B, the cosine similarity, cos(θ), is represented using
a dot product and magnitude as

24 | P a g e
 similarity = cos(Ø) = A.B\||A||||B||

Figure 9: Workflow of Content Based System

4.2. Tools Used

4.2.1. Analysis and Design Tools
 Content based filtering

4.2.2. Implementation Tools

 Front end: CSS, HTML, Java script
For the front-end development of our system, we have used CSS, HTML, Java script.
We have used HTML to draw the skeleton or to draw the outline of our system and
CSS and Java script are used to beautify the system.
 Backend: Python, Django
Python and Django are used as the backend tools. As we are using cosine similarity
algorithm, implementation of which is easy using python and Django.

4.2.3. Others Tools and Platforms

 GitHub
GitHub is a platform for code sharing and version controlling. In this project team
members were from different residential location so, there was necessity of
distributing working environment and for that GitHub was used for sharing the code.
Each team member would pull the project, add some functionality and push those
changes to the central repository to the GitHub.

25 | P a g e
  Visual Studio Code
Visual Studio Code is a versatile and fun text editor developed by Microsoft
repetitive tasks so you can focus the important stuff. It works on OS X, Windows and
Linux. It is highly customizable, allowing the user to change the theme, keywords
shortcut, preferences, and install extensions that add additional functionality.

4.2.4. Algorithm
 Cosine Similarity Measure
Cosine similarity [6] is a measure of similarity between two non-zero vectors of an
inner product space. It is defined to equal the cosine of the angle between them,
which is also the same as the inner product of the same vectors normalized to both
have length 1. The cosine of 0° is 1, and it is less than 1 for any angle in the interval
(0, π] radians. It is thus a judgment of orientation and not magnitude: two vectors
with the same orientation have a cosine similarity of 1, two vectors oriented at 90°
relative to each other have a similarity of 0, and two vectors diametrically opposed
have a similarity of -1, independent of their magnitude. The cosine similarity is
particularly used in positive space, where the outcome is neatly bounded in {\display
style [0,1]}[0,1]. The name derives from the term "direction cosine": in this case, unit
vectors are maximally "similar" if they're parallel and maximally "dissimilar" if
they're orthogonal (perpendicular). This is analogous to the cosine, which is unity
(maximum value) when the segments subtend a zero angle and zero (uncorrelated)
when the segments are perpendicular.

Algorithm we used for this project is:

Step1: Start
Step2: def cosine similarity (v1, v2,)
Step3: Initialized sumxx ,sumxy, sumyy = 0, 0, 0
Step4: Initialized i = 0
Step5: for I in range(len(v1))
x = v1[i]; y = v2[i]
sumxx += x**2

26 | P a g e
 sumyy += y**2
sumxy += x*y
i = i+1
Step6: return sumxy/math.sqrt(sumxx*sumyy)
Step7: End

4.3. Testing
During our development process we have carried out a series of testing to check the
differences between the given input and the expected output of our system. Finally, to see
whether or not the JRS works, different set of skills were passed through the system and the
output results are seen and compared to calculate accuracy and loss.

4.3.1. Unit Testing

After the work was divided and coding completed the modules were parallel tested and after
getting bug it was made bug free.

Test ID Test Unit Pre- Expected Actual Status

Condition/ Outcome Result
Test Data

1. Test if the User must be Recommend Recommend Pass

system logged in to the list of the job
recommends the system job as per
correct job the skill
as per the provide by
skill provide user
by user

2 Test if the Company Recommend Recommend Fail

. system must be the job to the job
recommends logged in to user
correct job the system according to
as per the the vacancy
vacancy/skill provided by
provide by the company

27 | P a g e
 company
3. Test if the Company Recommend Recommend Pass
system must be the job to the job
recommends logged in to user
correct job the system according to
as per the the vacancy
vacancy/skill provided by
provide by the company
company
Table 1: Unit Testing

4.3.2. Integration Testing

Test ID Test Unit Pre- Expected Actual Result Status
condition/Test Outcomes
Data

1. Run the User and Recommend Skill viewed fail

script by company the job to the and job is
integrating must be user recommended
skill provide logged in to the user
by user and
company
2. Run the User and Recommend Skill viewed pass
script by company the job to the and job is
integrating must be user recommended
skill provide logged in to the user
by user and
company
3. Run the User and Proper result Predicted fail
script by company by predicting result appears
integrating must provide the input
training and the skill skill in
classify file console
4. Run the User and Proper result Predicted pass
script by company by predicting result appears
integrating must provide the input
training and the skill skill in
classify file console
Table 2: Integration Testing

4.3.3. System Testing

Test ID Test Unit Pre- Expected Actual Status
condition/Test Outcomes Result
Data
1. Open the User must be Show the list Recommend fail
application logged in of vacancy the job as per

28 | P a g e
 and choose Select the as per the the
skill option skill skill provide information
and select by user provide by
the skill user
2. Open the User must be Show the list Recommend pass
application logged in and of vacancy the job as per
and choose Select the as per the the
skill option skill skill provide information
and select by user provide by
the skill user
3. Open the Company Show the list Recommend pass
application must be of vacancy to the job in
and add the logged in and the user as order of
vacancy by add the list of per the skill percentage to
company vacancy provided by the user
user
Table 3: System Testing

29 | P a g e
 Chapter 5

Maintenance and Support

5.1. Results
In this Section, each steps of methodology are implemented and results are described. As our
main motive is to recommend the job as per the skill provided by the user for the we have
used cosine similarity in which Euclidean distance is measured in order to calculate by how
much percentage the job is recommend to the user. And this system provides the accurate
result.

5.2. Maintenance and Support

We had put our full effort to develop this project so that all the required information to
maintain the system will be provide to the user. In case if somethings new happens then we
will happy to give support too.

As we develop this system in low cost so maintenance charge will be also low for this
system. We are planning to work on this project further so that whoever will use get the
update for the system whenever we make a change in system.

30 | P a g e
 Chapter 6

Conclusion and Recommendation

6.1. Conclusion

We addressed the problem of job

recommendation based on user
job application
history. We proposed different
personalised content-based and case-
based approaches
that use features ranging from
extracted features (bag-of-words and
entities) to mined
features (social tags) and explicit
features (job attributes, e.g. job
location, years of
experience and job education). We
also proposed a hybrid approach by
combining

31 | P a g e
content features with well-
structured features, along with
various feature-weighting
schemes for the case-based
approaches
We addressed the problem of job
recommendation based on user
job application
history. We proposed different
personalised content-based and case-
based approaches
that use features ranging from
extracted features (bag-of-words and
entities) to mined
features (social tags) and explicit
features (job attributes, e.g. job
location, years of

32 | P a g e
experience and job education). We
also proposed a hybrid approach by
combining
content features with well-
structured features, along with
various feature-weighting
schemes for the case-based
approaches
We addressed the problem of job
recommendation based on user
job application
history. We proposed different
personalised content-based and case-
based approaches
that use features ranging from
extracted features (bag-of-words and
entities) to mined

33 | P a g e
features (social tags) and explicit
features (job attributes, e.g. job
location, years of
experience and job education). We
also proposed a hybrid approach by
combining
content features with well-
structured features, along with
various feature-weighting
schemes for the case-based
approaches
We addressed the problem of job
recommendation based on user
job application
history. We proposed different
personalised content-based and case-
based approaches

34 | P a g e
that use features ranging from
extracted features (bag-of-words and
entities) to mined
features (social tags) and explicit
features (job attributes, e.g. job
location, years of
experience and job education). We
also proposed a hybrid approach by
combining
content features with well-
structured features, along with
various feature-weighting
schemes for the case-based
approaches.
We addressed the problem of job
recommendation based on user
job application

35 | P a g e
history. We proposed different
personalised content-based and case-
based approaches
that use features ranging from
extracted features (bag-of-words and
entities) to mined
features (social tags) and explicit
features (job attributes, e.g. job
location, years of
experience and job education). We
also proposed a hybrid approach by
combining
content features with well-
structured features, along with
various feature-weighting
schemes for the case-based
approaches.
The project has been developed successfully and the performance of the system has been
found good. Since, the project primary focuses on recommend the job as per the skill

36 | P a g e
provide, the system successfully provide the result my recommending the job to the user as
per the skill provided by users. The system is able to recommend the job.

6.2. Future Enhancement

In future work we plan to extend

our job recommendation
framework by
considering alternative content-
based job representations; for
example, by
representing jobs based on the
particular features of applicants.
Moreover, we will
apply collaborative-filtering style
approaches to the task, and consider
ways in which
the various approaches may be
combined to improve performance.
In future[7] work we plan to extend our job recommendation framework by considering
alternative content-based job representations; for example, by representing jobs based on the
particular features of applicants. Moreover, we will apply collaborative filtering style

37 | P a g e
approaches to the task and consider ways in which the various approaches may be combine
to improve the performances.

38 | P a g e
 REFERENCES
[1] M. M. a. A. M. R. Di Massa, "Implicit news recommendation based on user interest
models and multimodal content analysis," New work, USA, 2010.

[2] G. W. A. Y. C. Salton, A vector space model for automatic indexing, 1975.

[3] N. T. G. a. K. N. Almalis, "positions, A content based approach for recommending

personnel for job," in Proceedings of the 5th International Conference on Information,
Intelligence, Systems and Applications,IISA 2014, Chania, Greece, 2014.

[4] G. Salton, "Automatic Text Processing, The Transformation, Analysis, and Retrieval of
Information by Computer,," Addison-Wesley., 1989.

[5] P. N. N. Keita, "Web Recommender System for Job Seeking and Recruiting," Senegal, 31
January 2018.

[6] https://en.wikipedia.org/wiki/Cosine_similarity

[7]https://www.researchgate.net/publication/
266202751_An_Analysis_Framework_for_Content-based_Job_Recommendation

39 | P a g e
 Appendices

Figure 10: Home Page

40 | P a g e
Figure 11: Admin Panel

41 | P a g e
Figure 12:Registration Form for Company

42 | P a g e
Figure 13: Form to post vacancy

43 | P a g e
Figure 14:Registration Form for User

44 | P a g e
Figure 15:Recommended job to the User

45 | P a g e
Figure 16: Login Page for Admin

46 | P a g e
Figure 17:Algorithm Used

47 | P a g e