• 0 Review(s)

Product Category: Projects

Product Code: 00006481

No of Pages: 34

No of Chapters: 1-6

File Format: Microsoft Word

Price :



Recommender systems have been employed in entertainment, e-commerce, agriculture, healthcare and education among other industries to provide personalised suggestions to users. Recommender systems help to solve the problem a user being overburdened with information when using online systems. Due to digitization of the course application process in the institutions of higher learning, courses are now made available online in portals for students to apply. These courses are too many for the student to do adequate research before selection. This leads to students being selected to courses that they are not interested in and thus the need for a course recommendation system that suggests a short list of courses that are relevant to the student. This study focussed on developing a knowledge base recommender system prototype for providing personalised course recommendations to students based on their interests and performance. Knowledge based system development life cycle was used to develop the prototype and knowledge acquisition was done from domain experts and documented materials. To identify the interests, a questionnaire is administered. The Hollands three letter Code is then used to identify the personality. The personalities and results are then used to suggest a short list of courses that are relevant to the student. The model developed had an accuracy of 85.12% and thus can be used to recommend courses to students.


List of Figures 6
List of Tables 6

1.1 Background 7
1.2 Problem statement 8
1.3 Objectives 9
1.4 Significance of study 9
1.5 Stakeholders 9
1.6 Scope of Study 9

2.1 Introduction 10
2.2 Course Selection 10
2.2.1 Student Interests 10
2.2.2 Student Selection 11
2.3 Recommender systems 11
2.3.1 Types of recommender systems 12 Content Based Recommender Systems 12 Collaborative Filtering 12 Knowledge based recommender systems 13 Hybrid recommender systems 13
2.4 Related work 13
2.5 Gap 15
2.6 Conceptual Model 15

3.1 Research Framework 16
3.2 Research methods 18
3.2.1 Population and Sampling Technique 18
3.2.2 Data collection 18
3.2.3 Data preparation 19
3.2.4 Prototype Development 19
3.2.5 Evaluation 19
3.2.6 Ethical Considerations 19

4.1 Design Model 20
4.2 Personality Identifier 21
4.3 Course Qualification Identifier 23
4.4 Course Recommendation 27

5.1 Evaluation of the Prototype 29
5.2 Discussion 30

6.1 Conclusion 31
6.2 Recommendation 31

List of Figures

Figure 1: Holland Code Six Personality Types 11
Figure 2: Content Based Recommender System 12
Figure 3:Collaborative filtering Recommender Systems 13
Figure 4: Conceptual Model 15
Figure 5: Knowledge Base System Development Life Cycle 16
Figure 6 : Architecture of the Course Recommender Prototype 20
Figure 7: How personality test is administered 21
Figure 8: Code Extract that Administers Personality Test 22
Figure 9: Answers to an administered personality test 22
Figure 10: Code extract that prints all answers to an administered personality test. 22
Figure 11: Extract of code that calculates the three letter personality code and result 23
Figure 12: Bachelor of Science Mechanical Engineering minimum requirements. Obtained from KUCCPS students Portal (2021) 24
Figure 13: Extract of code that prints all available subjects from the knowledge base 25
Figure 14: Extract of sample student results 25
Figure 15: Extract of code, results and tracing of the process to check for cluster requirements 26
Figure 16: Sample extract showing the tracing of the process to check for sub cluster requirements 27
Figure 17: Extract of how the course recommendation is made 29

List of Tables

Table 1: Table showing the distribution of courses by personality and qualification type. 28 Table 2: Confusion matrix of the recommender system prototype 30 Table 3: Accuracy of the prototype 30


1.1 Background
Recommender systems have been used to provide suggestions that are a user’s preferences (Ricci, et al., 2015). With the availability of additional information to a user, it poses a challenge to them to go through all the information to identify what is relevant to them. A recommender system aims to provide a solution to the problem of a user being overburdened by information by ensuring the user experience is personalised and accurate personalised recommendations of items are delivered to the users of a system. Recommendation systems predict whether an item would be useful to a user based on information made available (Fayyaz, et al., 2020). Recommendation systems have been used in industries such as entertainment, e- commerce, healthcare, agriculture and education among others.

Students need guidance when selecting their course choices for higher education. In Kenya, students lack well planned and organised career guidance in schools (Ndung’u & Obae, 2020). According to (Crocker, 2002), the well-being of modern society is dependent not only on traditional capital and labour but also on the knowledge and ideas possessed and generated by individual workers. Therefore, education is the primary source of human capital with 90% of persons with higher education being likely to be employed than those with no formal education (Mulongo, 2013). In this regard, the government provides sponsorship through Kenya Universities and Colleges Central Placement Service (KUCCPS) that coordinates placement of government sponsored students and Universities Funding Board (UFB) which pays part of the fees required to be paid by the student to the universities (Universities Act, 2012). As recommended by (Mulongo, 2013), this enhances access to higher education and ensures that students who are victims of regional disparities caused by high cost of higher education coupled with remoteness and underdeveloped infrastructure enjoy equity.

With the introduction of the Government of Kenya’s a hundred percent transition policy, there has been a tremendous increase in enrolments across all public secondary schools in Kenya. This translates to an increase in competition for the available capacities for the existing courses. A significant number of students who secure admission into the universities through KUCCPS are neither offered degree courses of their choice nor placed in their preferred university (Ndung’u & Obae, 2020).This is majorly because students missing placement due to capacity being met in all of the course choices. The students are shared to other courses that have capacities not met and are similar to the courses they applied. Further, (Lugulu & Kipkoech, 2011) found out that 63.3% of students admitted in public universities were dissatisfied with the degree courses because they were placed in degree courses, they did not choose nor had a passion for. The choice of degree course made when joining universities is one of the series of decisions made in the process of career development and is a major turning point in the students’ lives which not only is a start to workplace readiness, but also establishes the student in a career path that opens as well as closes opportunities (Gacohi, 2017). (Nyamwange, 2016) recommends that students should be encouraged to make career choice decisions in areas they have or can acquire knowledge easily, skills and have interest as it is likely to promote productivity when the student is doing what they are interested in.

Career information is the provision of accurate and usable facts concerning university courses (Gibson & Mitchell, 2003). KUCCPS has developed a career book that provides insights into career opportunities, progression pathways, subject requirements for specific careers, and government-sponsored student placement processes. Students are given university course cut- offs over the previous years as insights to guide them during university course selection and to predict their placement to a university course.

An optimal course recommender system that uses student interests and performance to suggest a list of courses that match their interests and performance will ensure that students are selected to courses that they have interest and can acquire knowledge easily.

1.2 Problem statement
The main problem to be addressed by this research is that of students getting selected to courses that they have no interests, have difficulty in acquiring knowledge and information overload on students during application for admission to higher learning education institutions. Students having many choices to choose from and perform research on in order to identify a list of courses that they have interests makes it difficult for the students to make informed decisions. Information overload is caused by availability of many institutions offering many courses to be chosen from by a student. Students end up missing placement to the courses they selected due to lack of adequate guidance when selecting their course choices during an application period.

Therefore, there is a need to provide a solution that recommends a filtered list of courses to students based on their interests and performance.
1.3 Objectives
The main objective of this research is to develop a model for course recommendation that suggests a list of courses to a student based on their interests and performance.
Specific objectives:

1. To investigate how to incorporate student interests and performance to recommend courses.

2. To investigate which type of recommender system can be used to recommend courses to students based on their interests and performance.

3. To design a model for course recommendation to students.

4. To evaluate the model for course recommendation using a prototype.

1.4 Significance of study

The number of students enrolling into secondary schools has continued to rise since the introduction of the Free Primary Education in Kenya in 2003 leading to an increased demand to higher education in the country due to the realization that higher education forms the principal pillar of education. Regardless of the measures put to increase selection of students to higher education institutions, many of the students are still not guaranteed selection to courses that they have interest in. A course recommender system that will make use of the student performance and student interests will reduce the level of information overload and uncertainty by students during application for selection. This will lead to an increasing number of students getting selected to courses that they have interest in.

1.5 Stakeholders
The stakeholders that will be affected by the study will be as follows:

1. Students that will be making applications for higher education learning will have filtered and relevant information to work with as opposed to all information including what they would not choose.

2. Labour market. Students graduating will be passionate about their careers thus an increase in productivity.

1.6 Scope of Study
This paper will focus on developing and evaluating a course recommender system prototype that recommends courses to students based on student interests and their performance.

Click “DOWNLOAD NOW” below to get the complete Projects


+(234) 0814 780 1594

Buyers has the right to create dispute within seven (7) days of purchase for 100% refund request when you experience issue with the file received. 

Dispute can only be created when you receive a corrupt file, a wrong file or irregularities in the table of contents and content of the file you received. 

ProjectShelve.com shall either provide the appropriate file within 48hrs or send refund excluding your bank transaction charges. Term and Conditions are applied.

Buyers are expected to confirm that the material you are paying for is available on our website ProjectShelve.com and you have selected the right material, you have also gone through the preliminary pages and it interests you before payment. DO NOT MAKE BANK PAYMENT IF YOUR TOPIC IS NOT ON THE WEBSITE.

In case of payment for a material not available on ProjectShelve.com, the management of ProjectShelve.com has the right to keep your money until you send a topic that is available on our website within 48 hours.

You cannot change topic after receiving material of the topic you ordered and paid for.

Ratings & Reviews


No Review Found.

To Review

To Comment