SlideShare a Scribd company logo
Presentation for Software Engineering
Presented by
• Taminul Islam - 181-15-11116
• Rishalatun Jannat Lima - 181-15-11120
• Arindom Kundu - 181-15-10557
• Md Al-Amin Hosen - 181-15-11132
Presented to
Mr. Abdus Sattar
Assistant Professor
Department of Computer Science and Engineering
Daffodil International University
1
A Machine Learning Approach to Performance and Dropout
prediction in Computer Science: Bangladesh Perspective
Title
Sheikh Arif Ahmed Md. Aref Billah Shahidul Islam Khan
2
Reference: Ahmed, S. A., Billah, M. A., & Khan, S. I. (2020, July). A Machine Learning Approach to Performance and Dropout prediction in Computer Science: Bangladesh Perspective. In 2020 11th
International Conference on Computing, Communication and Networking Technologies (ICCCNT) (pp. 1-6). IEEE.
Abstract
Nowadays Computer Science (C.S.) and other technology-related subjects are a hot cake for the students. Due to a
good job market for these subjects, students are taking computer science and other related topics without thinking
about their capability and without knowing the curriculum of these subjects. So the dropout rate is getting high day
by day in these subjects. Especially developing countries like Bangladesh. In this work, they have used current
computer science students’ data to predict their and also prospective C.S. students’ future performance and the
chance of dropout using machine learning algorithms.
They have used SVM, naïve Bayes, neural network, etc. They have also predicted the crucial factors that are strongly
correlated to the performance of a C.S. student.
3
Introduction
 Objectives
 To track down the original reasons behind the Dropout of Computer Science graduates.
 To predict and prospective Computer Science students’ future performance
 To predict the chance of dropout
 To predicted the crucial factors which are strongly correlated to the performance of a Computer Science student.
4
Introduction
 Research Goal
Taking Computer Science students live and current data from all over the world then create an algorithm to predict
the future performance and the chance of dropout using machine learning algorithms like SVM, naïve Bayes, neural
network.
Also predict the crucial factors that are strongly correlated to the performance of a C.S. student. Finding reasons
behind the dropout on Computer Science students.
5
Introduction
 Research Question
1. What are the actual reason behind the dropout on Computer Science students ?
2. How a dropout student contributes in the global world nationally & internationally ?
3. What are the main factors behind the success and failure of a dropout student on C.S department ?
4. What are the most efficient indicators to analysis a student ?
5. How to make development of a C.S student to avoiding dropout ?
6
Literature Review
 Dropout Prediction
• Ahmed and Khan discovered few essential features like the previous result, math score of school-level, etc. responsible for
student dropout while predicting the perspective dropout student using machine learning.
He also showed, how CGPA and programming skill impacts future dropouts.
• Vinayak and Prageeth predicted students dropout using 54 attributes, which includes personal and health information as well as
the previous academic data.
• Costa et al. used only a course data to predict perspective dropout students. While Boris et al. didn’t take any survey from
students. They took data from institutions to make their dropout prediction model using machine learning algorithms
7
Literature Review
 Performance Prediction
• Alharbi et al. collected students’ data to predict the performance after completing one year in the university
• Baradwaj & Pal predicted students’ performance using a database collected from the university, which includes their personal
and academic data they filled up during admission.
• Goga et al. proposed a tool using classification algorithms to predict students’ performance. They used multi-layer perceptions,
random forests, etc. to build the model.
• Arsad & Buniyamin found that whoever has a good foundation for the previous study has an excellent performance.
8
Research Methods
 Data Collection and Preprocessing
Using the questionnaire, data were
collected through IBM SPSS and
Google Form.
Figure 1- Attributes Overview
9
Research Methods
 Data Collection and Preprocessing
Figure 2 shows the options with
correspondent values, and short
term of the survey questionnaire
Figure 2- Short Terms
10
Research Methods
 Data Collection and Preprocessing
Table 1:
Students related variables that illustrate
the questions they asked the students and
probable answers.
Table 1
11
Research Methods
 Data Collection and Preprocessing
They have collected data from the current C.S. student of various universities
from the diverse city of Bangladesh. Table II shows the frequency of gender
from the dataset.
Table III shows the sample rule generation for the new feature
creation.
12
Research Methods
 Data Mining
In this section, they have showed a
successful way to make prediction
model by classification via clustering
method which we have followed as a
structure.
i) Predicted Programming Skill and
CGPA
ii) Predicted the chances of dropout
Figure 3. Model workflow Overview
13
Main Work
Predicting Programming Skill and CGPA
The decision tree , SVM, Neural network and Random Forest was used for building the model. While
predicting the CGPA, they had to group the CGPA on a scale of 1 to 5, which shown in table 8.
14
Main Work
Then they have predicted the CGPA and Programming Skill using different algorithms. Figure 4 shows the model
building process-
Figure 4. Prediction model for Predicting CGPA and Programming Skill.
15
Main Work
CGPA Prediction
For an illustration of results, we used R.O.C. curves with F.P. rate (Specificity) in the X-axis and T.P. rate
(Sensitivity) in the Y-Axis ( figure 5,7 and 9)
Results show “Random Forest” algorithms perform better than others. For further evaluation, the R.O.C. curve is
shown in Figure 5-
16
Main Work
Programing Skill Prediction
Figure 6. Results of Programming Skill Prediction
17
Main Work
Dropout Prediction
Figure 8. Results for Predicting Dropout
18
Result & Conclusion
Unlike other dropout prediction works, they have taken a few attributes related to C.S. Again proved that
CGPA and Programming skill is very crucial for predicting perspective dropout.
This model can predict and notify a student before starting the undergraduate program, whether they are fit
for a C.S. undergraduate. Also, students can know how their CGPA and programming skill will be using
their current data.
the results of the dropout prediction model say all — best Accuracy by the Neural network, which is
98.2%.
This work can be beneficial to the students, whoever thinking of starting an undergraduate in CS-related
subjects but not limited to them.
Also, the students in the midway can take help from the predicted feature set for a good result and
programming skill to have a bright career.
19
Motivation from this study
Absolutely this is an outstanding achievement for Bangladeshi researcher. This study provides 98.2%
accuracy, which is marvelous.
1) They have discovered the ten most influential features to get success in C.S.E. Predicting CGPA,
Programing skills and dropout classifier is most important for a student. This is a great contribution on
education sector.
2) They have also predicted the final result & performance.
3) Students will be benefitted more by implementing this study.
4) This will help to produce the productive person in the job market specially in CSE background.
5) Discovering essential factor for an excellence performance is one of the biggest achievement from this
study.
20
FAQ
21
Thank You
22

More Related Content

What's hot

Algorithm and Data Structure - Introduction
Algorithm and Data Structure - IntroductionAlgorithm and Data Structure - Introduction
Algorithm and Data Structure - Introduction
AndiNurkholis1
 
Algorithm and Data Structure - Concept of Algorithm and Data Structure
Algorithm and Data Structure - Concept of Algorithm and Data StructureAlgorithm and Data Structure - Concept of Algorithm and Data Structure
Algorithm and Data Structure - Concept of Algorithm and Data Structure
AndiNurkholis1
 
RESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATION
RESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATIONRESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATION
RESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATION
International Journal of Technical Research & Application
 
Predicting students performance in final examination
Predicting students performance in final examinationPredicting students performance in final examination
Predicting students performance in final examination
Rashid Ansari
 
Mba lab with CO
Mba lab with COMba lab with CO
Mba lab with CO
csehod2
 
Abstract and ToC
Abstract and ToCAbstract and ToC
Abstract and ToCJanet Price
 
Data Mining Techniques for School Failure and Dropout System
Data Mining Techniques for School Failure and Dropout SystemData Mining Techniques for School Failure and Dropout System
Data Mining Techniques for School Failure and Dropout System
Kumar Goud
 
Short story ppt
Short story pptShort story ppt
Short story ppt
KarishmaKuria1
 
Short story ppt
Short story pptShort story ppt
Short story ppt
KarishmaKuria1
 
2019 DSA 105 Introduction to Data Science Week 5
2019 DSA 105 Introduction to Data Science Week 52019 DSA 105 Introduction to Data Science Week 5
2019 DSA 105 Introduction to Data Science Week 5
Ferdin Joe John Joseph PhD
 
Modeling the Student Success or Failure in Engineering at VUT Using the Date ...
Modeling the Student Success or Failure in Engineering at VUT Using the Date ...Modeling the Student Success or Failure in Engineering at VUT Using the Date ...
Modeling the Student Success or Failure in Engineering at VUT Using the Date ...
journal ijrtem
 
Colour Models of Computer Graphics
Colour Models of Computer GraphicsColour Models of Computer Graphics
Resume
ResumeResume
Resume
TEJAL PATEL
 
Recommendation Model for Students
Recommendation Model for StudentsRecommendation Model for Students
Recommendation Model for Students
Mphasis
 
Educational Data Mining & Students Performance Prediction using SVM Techniques
Educational Data Mining & Students Performance Prediction using SVM TechniquesEducational Data Mining & Students Performance Prediction using SVM Techniques
Educational Data Mining & Students Performance Prediction using SVM Techniques
IRJET Journal
 
IRJET- Analysis of Student Performance using Machine Learning Techniques
IRJET- Analysis of Student Performance using Machine Learning TechniquesIRJET- Analysis of Student Performance using Machine Learning Techniques
IRJET- Analysis of Student Performance using Machine Learning Techniques
IRJET Journal
 
Data Science, Big Data, Data Analytics
Data Science, Big Data, Data AnalyticsData Science, Big Data, Data Analytics
Data Science, Big Data, Data Analytics
International Institute of Information Technology (I²IT)
 
Interfacing of LCD with LPC2148
Interfacing of LCD with LPC2148Interfacing of LCD with LPC2148
What Is High Performance-Computing?
What Is High Performance-Computing?What Is High Performance-Computing?

What's hot (20)

Algorithm and Data Structure - Introduction
Algorithm and Data Structure - IntroductionAlgorithm and Data Structure - Introduction
Algorithm and Data Structure - Introduction
 
Algorithm and Data Structure - Concept of Algorithm and Data Structure
Algorithm and Data Structure - Concept of Algorithm and Data StructureAlgorithm and Data Structure - Concept of Algorithm and Data Structure
Algorithm and Data Structure - Concept of Algorithm and Data Structure
 
RESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATION
RESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATIONRESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATION
RESULT MINING: ANALYSIS OF DATA MINING TECHNIQUES IN EDUCATION
 
Predicting students performance in final examination
Predicting students performance in final examinationPredicting students performance in final examination
Predicting students performance in final examination
 
Seyedi-curriculum vitae
Seyedi-curriculum vitaeSeyedi-curriculum vitae
Seyedi-curriculum vitae
 
Mba lab with CO
Mba lab with COMba lab with CO
Mba lab with CO
 
Abstract and ToC
Abstract and ToCAbstract and ToC
Abstract and ToC
 
Data Mining Techniques for School Failure and Dropout System
Data Mining Techniques for School Failure and Dropout SystemData Mining Techniques for School Failure and Dropout System
Data Mining Techniques for School Failure and Dropout System
 
Short story ppt
Short story pptShort story ppt
Short story ppt
 
Short story ppt
Short story pptShort story ppt
Short story ppt
 
2019 DSA 105 Introduction to Data Science Week 5
2019 DSA 105 Introduction to Data Science Week 52019 DSA 105 Introduction to Data Science Week 5
2019 DSA 105 Introduction to Data Science Week 5
 
Modeling the Student Success or Failure in Engineering at VUT Using the Date ...
Modeling the Student Success or Failure in Engineering at VUT Using the Date ...Modeling the Student Success or Failure in Engineering at VUT Using the Date ...
Modeling the Student Success or Failure in Engineering at VUT Using the Date ...
 
Colour Models of Computer Graphics
Colour Models of Computer GraphicsColour Models of Computer Graphics
Colour Models of Computer Graphics
 
Resume
ResumeResume
Resume
 
Recommendation Model for Students
Recommendation Model for StudentsRecommendation Model for Students
Recommendation Model for Students
 
Educational Data Mining & Students Performance Prediction using SVM Techniques
Educational Data Mining & Students Performance Prediction using SVM TechniquesEducational Data Mining & Students Performance Prediction using SVM Techniques
Educational Data Mining & Students Performance Prediction using SVM Techniques
 
IRJET- Analysis of Student Performance using Machine Learning Techniques
IRJET- Analysis of Student Performance using Machine Learning TechniquesIRJET- Analysis of Student Performance using Machine Learning Techniques
IRJET- Analysis of Student Performance using Machine Learning Techniques
 
Data Science, Big Data, Data Analytics
Data Science, Big Data, Data AnalyticsData Science, Big Data, Data Analytics
Data Science, Big Data, Data Analytics
 
Interfacing of LCD with LPC2148
Interfacing of LCD with LPC2148Interfacing of LCD with LPC2148
Interfacing of LCD with LPC2148
 
What Is High Performance-Computing?
What Is High Performance-Computing?What Is High Performance-Computing?
What Is High Performance-Computing?
 

Similar to Paper Presentation

ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...
ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...
ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...
indexPub
 
Ijciet 10 02_007
Ijciet 10 02_007Ijciet 10 02_007
Ijciet 10 02_007
IAEME Publication
 
Learning Analytics for Computer Programming Education
Learning Analytics for Computer Programming EducationLearning Analytics for Computer Programming Education
Learning Analytics for Computer Programming Education
IRJET Journal
 
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
Editor IJCATR
 
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
Editor IJCATR
 
An Intelligent Career Guidance System using Machine Learning
An Intelligent Career Guidance System using Machine LearningAn Intelligent Career Guidance System using Machine Learning
An Intelligent Career Guidance System using Machine Learning
IRJET Journal
 
Student’s Career Interest Prediction using Machine Learning
Student’s Career Interest Prediction using Machine LearningStudent’s Career Interest Prediction using Machine Learning
Student’s Career Interest Prediction using Machine Learning
IRJET Journal
 
IRJET- Evaluation Technique of Student Performance in various Courses
IRJET- Evaluation Technique of Student Performance in various CoursesIRJET- Evaluation Technique of Student Performance in various Courses
IRJET- Evaluation Technique of Student Performance in various Courses
IRJET Journal
 
UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...
UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...
UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...
IRJET Journal
 
University Recommendation Support System using ML Algorithms
University Recommendation Support System using ML AlgorithmsUniversity Recommendation Support System using ML Algorithms
University Recommendation Support System using ML Algorithms
IRJET Journal
 
Big data project
Big data projectBig data project
Big data project
Kedar Kumar
 
IRJET- Performance for Student Higher Education using Decision Tree to Predic...
IRJET- Performance for Student Higher Education using Decision Tree to Predic...IRJET- Performance for Student Higher Education using Decision Tree to Predic...
IRJET- Performance for Student Higher Education using Decision Tree to Predic...
IRJET Journal
 
Intelligent Career Guidance System.pptx
Intelligent Career Guidance System.pptxIntelligent Career Guidance System.pptx
Intelligent Career Guidance System.pptx
Anonymous366406
 
scopus journal.pdf
scopus journal.pdfscopus journal.pdf
scopus journal.pdf
nareshkotra
 
Journal publications
Journal publicationsJournal publications
Journal publications
Sarita30844
 
IJMERT.pdf
IJMERT.pdfIJMERT.pdf
IJMERT.pdf
nareshkotra
 
IRJET- Student Performance Analysis System for Higher Secondary Education
IRJET- Student Performance Analysis System for Higher Secondary EducationIRJET- Student Performance Analysis System for Higher Secondary Education
IRJET- Student Performance Analysis System for Higher Secondary Education
IRJET Journal
 
Factors that contribute programming skill and CGPA as a CS graduate: Mining E...
Factors that contribute programming skill and CGPA as a CS graduate: Mining E...Factors that contribute programming skill and CGPA as a CS graduate: Mining E...
Factors that contribute programming skill and CGPA as a CS graduate: Mining E...
Sakibhasan63
 
journal for research
journal for researchjournal for research
journal for research
graphicdesigner79
 
IRJET - A Study on Student Career Prediction
IRJET - A Study on Student Career PredictionIRJET - A Study on Student Career Prediction
IRJET - A Study on Student Career Prediction
IRJET Journal
 

Similar to Paper Presentation (20)

ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...
ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...
ANALYSIS OF STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS:– ...
 
Ijciet 10 02_007
Ijciet 10 02_007Ijciet 10 02_007
Ijciet 10 02_007
 
Learning Analytics for Computer Programming Education
Learning Analytics for Computer Programming EducationLearning Analytics for Computer Programming Education
Learning Analytics for Computer Programming Education
 
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
 
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
A Model for Predicting Students’ Academic Performance using a Hybrid of K-mea...
 
An Intelligent Career Guidance System using Machine Learning
An Intelligent Career Guidance System using Machine LearningAn Intelligent Career Guidance System using Machine Learning
An Intelligent Career Guidance System using Machine Learning
 
Student’s Career Interest Prediction using Machine Learning
Student’s Career Interest Prediction using Machine LearningStudent’s Career Interest Prediction using Machine Learning
Student’s Career Interest Prediction using Machine Learning
 
IRJET- Evaluation Technique of Student Performance in various Courses
IRJET- Evaluation Technique of Student Performance in various CoursesIRJET- Evaluation Technique of Student Performance in various Courses
IRJET- Evaluation Technique of Student Performance in various Courses
 
UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...
UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...
UNIVERSITY ADMISSION SYSTEMS USING DATA MINING TECHNIQUES TO PREDICT STUDENT ...
 
University Recommendation Support System using ML Algorithms
University Recommendation Support System using ML AlgorithmsUniversity Recommendation Support System using ML Algorithms
University Recommendation Support System using ML Algorithms
 
Big data project
Big data projectBig data project
Big data project
 
IRJET- Performance for Student Higher Education using Decision Tree to Predic...
IRJET- Performance for Student Higher Education using Decision Tree to Predic...IRJET- Performance for Student Higher Education using Decision Tree to Predic...
IRJET- Performance for Student Higher Education using Decision Tree to Predic...
 
Intelligent Career Guidance System.pptx
Intelligent Career Guidance System.pptxIntelligent Career Guidance System.pptx
Intelligent Career Guidance System.pptx
 
scopus journal.pdf
scopus journal.pdfscopus journal.pdf
scopus journal.pdf
 
Journal publications
Journal publicationsJournal publications
Journal publications
 
IJMERT.pdf
IJMERT.pdfIJMERT.pdf
IJMERT.pdf
 
IRJET- Student Performance Analysis System for Higher Secondary Education
IRJET- Student Performance Analysis System for Higher Secondary EducationIRJET- Student Performance Analysis System for Higher Secondary Education
IRJET- Student Performance Analysis System for Higher Secondary Education
 
Factors that contribute programming skill and CGPA as a CS graduate: Mining E...
Factors that contribute programming skill and CGPA as a CS graduate: Mining E...Factors that contribute programming skill and CGPA as a CS graduate: Mining E...
Factors that contribute programming skill and CGPA as a CS graduate: Mining E...
 
journal for research
journal for researchjournal for research
journal for research
 
IRJET - A Study on Student Career Prediction
IRJET - A Study on Student Career PredictionIRJET - A Study on Student Career Prediction
IRJET - A Study on Student Career Prediction
 

More from Taminul Islam

Cardiovascular Disease Prediction Using Machine Learning Approaches.pptx
Cardiovascular Disease Prediction Using Machine Learning Approaches.pptxCardiovascular Disease Prediction Using Machine Learning Approaches.pptx
Cardiovascular Disease Prediction Using Machine Learning Approaches.pptx
Taminul Islam
 
Is Simulation Blessing or Curse?
Is Simulation Blessing or Curse?Is Simulation Blessing or Curse?
Is Simulation Blessing or Curse?
Taminul Islam
 
Hello cox's bazar
Hello cox's bazarHello cox's bazar
Hello cox's bazar
Taminul Islam
 
Human vs computer
Human vs computerHuman vs computer
Human vs computer
Taminul Islam
 
Memory Organization of a Computer System
Memory Organization of a Computer SystemMemory Organization of a Computer System
Memory Organization of a Computer System
Taminul Islam
 
The Basic Configuration of a Microcomputer
The Basic Configuration of a Microcomputer The Basic Configuration of a Microcomputer
The Basic Configuration of a Microcomputer
Taminul Islam
 
Efficient way of searching Google
Efficient way of searching GoogleEfficient way of searching Google
Efficient way of searching Google
Taminul Islam
 
Mechanics
MechanicsMechanics
Mechanics
Taminul Islam
 
Google Home Mini
Google Home MiniGoogle Home Mini
Google Home Mini
Taminul Islam
 
Breadth First Search
Breadth First Search Breadth First Search
Breadth First Search
Taminul Islam
 
JFET
JFETJFET
Solution of Traffic Jam
Solution of Traffic Jam Solution of Traffic Jam
Solution of Traffic Jam
Taminul Islam
 
Telecommunication Sector in Bangladesh
Telecommunication Sector in BangladeshTelecommunication Sector in Bangladesh
Telecommunication Sector in Bangladesh
Taminul Islam
 
Breath First Search
Breath First SearchBreath First Search
Breath First Search
Taminul Islam
 
Bangladesh in the world of cricket
Bangladesh in the world of cricketBangladesh in the world of cricket
Bangladesh in the world of cricket
Taminul Islam
 
Artificial Intelligence
Artificial Intelligence Artificial Intelligence
Artificial Intelligence
Taminul Islam
 
Present Tense Presentation
Present Tense Presentation Present Tense Presentation
Present Tense Presentation
Taminul Islam
 

More from Taminul Islam (17)

Cardiovascular Disease Prediction Using Machine Learning Approaches.pptx
Cardiovascular Disease Prediction Using Machine Learning Approaches.pptxCardiovascular Disease Prediction Using Machine Learning Approaches.pptx
Cardiovascular Disease Prediction Using Machine Learning Approaches.pptx
 
Is Simulation Blessing or Curse?
Is Simulation Blessing or Curse?Is Simulation Blessing or Curse?
Is Simulation Blessing or Curse?
 
Hello cox's bazar
Hello cox's bazarHello cox's bazar
Hello cox's bazar
 
Human vs computer
Human vs computerHuman vs computer
Human vs computer
 
Memory Organization of a Computer System
Memory Organization of a Computer SystemMemory Organization of a Computer System
Memory Organization of a Computer System
 
The Basic Configuration of a Microcomputer
The Basic Configuration of a Microcomputer The Basic Configuration of a Microcomputer
The Basic Configuration of a Microcomputer
 
Efficient way of searching Google
Efficient way of searching GoogleEfficient way of searching Google
Efficient way of searching Google
 
Mechanics
MechanicsMechanics
Mechanics
 
Google Home Mini
Google Home MiniGoogle Home Mini
Google Home Mini
 
Breadth First Search
Breadth First Search Breadth First Search
Breadth First Search
 
JFET
JFETJFET
JFET
 
Solution of Traffic Jam
Solution of Traffic Jam Solution of Traffic Jam
Solution of Traffic Jam
 
Telecommunication Sector in Bangladesh
Telecommunication Sector in BangladeshTelecommunication Sector in Bangladesh
Telecommunication Sector in Bangladesh
 
Breath First Search
Breath First SearchBreath First Search
Breath First Search
 
Bangladesh in the world of cricket
Bangladesh in the world of cricketBangladesh in the world of cricket
Bangladesh in the world of cricket
 
Artificial Intelligence
Artificial Intelligence Artificial Intelligence
Artificial Intelligence
 
Present Tense Presentation
Present Tense Presentation Present Tense Presentation
Present Tense Presentation
 

Recently uploaded

Lapbook sobre os Regimes Totalitários.pdf
Lapbook sobre os Regimes Totalitários.pdfLapbook sobre os Regimes Totalitários.pdf
Lapbook sobre os Regimes Totalitários.pdf
Jean Carlos Nunes Paixão
 
Normal Labour/ Stages of Labour/ Mechanism of Labour
Normal Labour/ Stages of Labour/ Mechanism of LabourNormal Labour/ Stages of Labour/ Mechanism of Labour
Normal Labour/ Stages of Labour/ Mechanism of Labour
Wasim Ak
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
Special education needs
 
1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx
JosvitaDsouza2
 
Acetabularia Information For Class 9 .docx
Acetabularia Information For Class 9  .docxAcetabularia Information For Class 9  .docx
Acetabularia Information For Class 9 .docx
vaibhavrinwa19
 
STRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBC
STRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBCSTRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBC
STRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBC
kimdan468
 
2024.06.01 Introducing a competency framework for languag learning materials ...
2024.06.01 Introducing a competency framework for languag learning materials ...2024.06.01 Introducing a competency framework for languag learning materials ...
2024.06.01 Introducing a competency framework for languag learning materials ...
Sandy Millin
 
Synthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptxSynthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptx
Pavel ( NSTU)
 
How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...
Jisc
 
The approach at University of Liverpool.pptx
The approach at University of Liverpool.pptxThe approach at University of Liverpool.pptx
The approach at University of Liverpool.pptx
Jisc
 
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama UniversityNatural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
Akanksha trivedi rama nursing college kanpur.
 
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdfMASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
goswamiyash170123
 
Digital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and ResearchDigital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and Research
Vikramjit Singh
 
Guidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th SemesterGuidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th Semester
Atul Kumar Singh
 
The Challenger.pdf DNHS Official Publication
The Challenger.pdf DNHS Official PublicationThe Challenger.pdf DNHS Official Publication
The Challenger.pdf DNHS Official Publication
Delapenabediema
 
Chapter -12, Antibiotics (One Page Notes).pdf
Chapter -12, Antibiotics (One Page Notes).pdfChapter -12, Antibiotics (One Page Notes).pdf
Chapter -12, Antibiotics (One Page Notes).pdf
Kartik Tiwari
 
Unit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdfUnit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdf
Thiyagu K
 
The basics of sentences session 5pptx.pptx
The basics of sentences session 5pptx.pptxThe basics of sentences session 5pptx.pptx
The basics of sentences session 5pptx.pptx
heathfieldcps1
 
"Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe..."Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe...
SACHIN R KONDAGURI
 
Model Attribute Check Company Auto Property
Model Attribute  Check Company Auto PropertyModel Attribute  Check Company Auto Property
Model Attribute Check Company Auto Property
Celine George
 

Recently uploaded (20)

Lapbook sobre os Regimes Totalitários.pdf
Lapbook sobre os Regimes Totalitários.pdfLapbook sobre os Regimes Totalitários.pdf
Lapbook sobre os Regimes Totalitários.pdf
 
Normal Labour/ Stages of Labour/ Mechanism of Labour
Normal Labour/ Stages of Labour/ Mechanism of LabourNormal Labour/ Stages of Labour/ Mechanism of Labour
Normal Labour/ Stages of Labour/ Mechanism of Labour
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
 
1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx
 
Acetabularia Information For Class 9 .docx
Acetabularia Information For Class 9  .docxAcetabularia Information For Class 9  .docx
Acetabularia Information For Class 9 .docx
 
STRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBC
STRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBCSTRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBC
STRAND 3 HYGIENIC PRACTICES.pptx GRADE 7 CBC
 
2024.06.01 Introducing a competency framework for languag learning materials ...
2024.06.01 Introducing a competency framework for languag learning materials ...2024.06.01 Introducing a competency framework for languag learning materials ...
2024.06.01 Introducing a competency framework for languag learning materials ...
 
Synthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptxSynthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptx
 
How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...
 
The approach at University of Liverpool.pptx
The approach at University of Liverpool.pptxThe approach at University of Liverpool.pptx
The approach at University of Liverpool.pptx
 
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama UniversityNatural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
 
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdfMASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
MASS MEDIA STUDIES-835-CLASS XI Resource Material.pdf
 
Digital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and ResearchDigital Tools and AI for Teaching Learning and Research
Digital Tools and AI for Teaching Learning and Research
 
Guidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th SemesterGuidance_and_Counselling.pdf B.Ed. 4th Semester
Guidance_and_Counselling.pdf B.Ed. 4th Semester
 
The Challenger.pdf DNHS Official Publication
The Challenger.pdf DNHS Official PublicationThe Challenger.pdf DNHS Official Publication
The Challenger.pdf DNHS Official Publication
 
Chapter -12, Antibiotics (One Page Notes).pdf
Chapter -12, Antibiotics (One Page Notes).pdfChapter -12, Antibiotics (One Page Notes).pdf
Chapter -12, Antibiotics (One Page Notes).pdf
 
Unit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdfUnit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdf
 
The basics of sentences session 5pptx.pptx
The basics of sentences session 5pptx.pptxThe basics of sentences session 5pptx.pptx
The basics of sentences session 5pptx.pptx
 
"Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe..."Protectable subject matters, Protection in biotechnology, Protection of othe...
"Protectable subject matters, Protection in biotechnology, Protection of othe...
 
Model Attribute Check Company Auto Property
Model Attribute  Check Company Auto PropertyModel Attribute  Check Company Auto Property
Model Attribute Check Company Auto Property
 

Paper Presentation

  • 1. Presentation for Software Engineering Presented by • Taminul Islam - 181-15-11116 • Rishalatun Jannat Lima - 181-15-11120 • Arindom Kundu - 181-15-10557 • Md Al-Amin Hosen - 181-15-11132 Presented to Mr. Abdus Sattar Assistant Professor Department of Computer Science and Engineering Daffodil International University 1
  • 2. A Machine Learning Approach to Performance and Dropout prediction in Computer Science: Bangladesh Perspective Title Sheikh Arif Ahmed Md. Aref Billah Shahidul Islam Khan 2 Reference: Ahmed, S. A., Billah, M. A., & Khan, S. I. (2020, July). A Machine Learning Approach to Performance and Dropout prediction in Computer Science: Bangladesh Perspective. In 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT) (pp. 1-6). IEEE.
  • 3. Abstract Nowadays Computer Science (C.S.) and other technology-related subjects are a hot cake for the students. Due to a good job market for these subjects, students are taking computer science and other related topics without thinking about their capability and without knowing the curriculum of these subjects. So the dropout rate is getting high day by day in these subjects. Especially developing countries like Bangladesh. In this work, they have used current computer science students’ data to predict their and also prospective C.S. students’ future performance and the chance of dropout using machine learning algorithms. They have used SVM, naïve Bayes, neural network, etc. They have also predicted the crucial factors that are strongly correlated to the performance of a C.S. student. 3
  • 4. Introduction  Objectives  To track down the original reasons behind the Dropout of Computer Science graduates.  To predict and prospective Computer Science students’ future performance  To predict the chance of dropout  To predicted the crucial factors which are strongly correlated to the performance of a Computer Science student. 4
  • 5. Introduction  Research Goal Taking Computer Science students live and current data from all over the world then create an algorithm to predict the future performance and the chance of dropout using machine learning algorithms like SVM, naïve Bayes, neural network. Also predict the crucial factors that are strongly correlated to the performance of a C.S. student. Finding reasons behind the dropout on Computer Science students. 5
  • 6. Introduction  Research Question 1. What are the actual reason behind the dropout on Computer Science students ? 2. How a dropout student contributes in the global world nationally & internationally ? 3. What are the main factors behind the success and failure of a dropout student on C.S department ? 4. What are the most efficient indicators to analysis a student ? 5. How to make development of a C.S student to avoiding dropout ? 6
  • 7. Literature Review  Dropout Prediction • Ahmed and Khan discovered few essential features like the previous result, math score of school-level, etc. responsible for student dropout while predicting the perspective dropout student using machine learning. He also showed, how CGPA and programming skill impacts future dropouts. • Vinayak and Prageeth predicted students dropout using 54 attributes, which includes personal and health information as well as the previous academic data. • Costa et al. used only a course data to predict perspective dropout students. While Boris et al. didn’t take any survey from students. They took data from institutions to make their dropout prediction model using machine learning algorithms 7
  • 8. Literature Review  Performance Prediction • Alharbi et al. collected students’ data to predict the performance after completing one year in the university • Baradwaj & Pal predicted students’ performance using a database collected from the university, which includes their personal and academic data they filled up during admission. • Goga et al. proposed a tool using classification algorithms to predict students’ performance. They used multi-layer perceptions, random forests, etc. to build the model. • Arsad & Buniyamin found that whoever has a good foundation for the previous study has an excellent performance. 8
  • 9. Research Methods  Data Collection and Preprocessing Using the questionnaire, data were collected through IBM SPSS and Google Form. Figure 1- Attributes Overview 9
  • 10. Research Methods  Data Collection and Preprocessing Figure 2 shows the options with correspondent values, and short term of the survey questionnaire Figure 2- Short Terms 10
  • 11. Research Methods  Data Collection and Preprocessing Table 1: Students related variables that illustrate the questions they asked the students and probable answers. Table 1 11
  • 12. Research Methods  Data Collection and Preprocessing They have collected data from the current C.S. student of various universities from the diverse city of Bangladesh. Table II shows the frequency of gender from the dataset. Table III shows the sample rule generation for the new feature creation. 12
  • 13. Research Methods  Data Mining In this section, they have showed a successful way to make prediction model by classification via clustering method which we have followed as a structure. i) Predicted Programming Skill and CGPA ii) Predicted the chances of dropout Figure 3. Model workflow Overview 13
  • 14. Main Work Predicting Programming Skill and CGPA The decision tree , SVM, Neural network and Random Forest was used for building the model. While predicting the CGPA, they had to group the CGPA on a scale of 1 to 5, which shown in table 8. 14
  • 15. Main Work Then they have predicted the CGPA and Programming Skill using different algorithms. Figure 4 shows the model building process- Figure 4. Prediction model for Predicting CGPA and Programming Skill. 15
  • 16. Main Work CGPA Prediction For an illustration of results, we used R.O.C. curves with F.P. rate (Specificity) in the X-axis and T.P. rate (Sensitivity) in the Y-Axis ( figure 5,7 and 9) Results show “Random Forest” algorithms perform better than others. For further evaluation, the R.O.C. curve is shown in Figure 5- 16
  • 17. Main Work Programing Skill Prediction Figure 6. Results of Programming Skill Prediction 17
  • 18. Main Work Dropout Prediction Figure 8. Results for Predicting Dropout 18
  • 19. Result & Conclusion Unlike other dropout prediction works, they have taken a few attributes related to C.S. Again proved that CGPA and Programming skill is very crucial for predicting perspective dropout. This model can predict and notify a student before starting the undergraduate program, whether they are fit for a C.S. undergraduate. Also, students can know how their CGPA and programming skill will be using their current data. the results of the dropout prediction model say all — best Accuracy by the Neural network, which is 98.2%. This work can be beneficial to the students, whoever thinking of starting an undergraduate in CS-related subjects but not limited to them. Also, the students in the midway can take help from the predicted feature set for a good result and programming skill to have a bright career. 19
  • 20. Motivation from this study Absolutely this is an outstanding achievement for Bangladeshi researcher. This study provides 98.2% accuracy, which is marvelous. 1) They have discovered the ten most influential features to get success in C.S.E. Predicting CGPA, Programing skills and dropout classifier is most important for a student. This is a great contribution on education sector. 2) They have also predicted the final result & performance. 3) Students will be benefitted more by implementing this study. 4) This will help to produce the productive person in the job market specially in CSE background. 5) Discovering essential factor for an excellence performance is one of the biggest achievement from this study. 20