SlideShare ist ein Scribd-Unternehmen logo
1 von 39
Machine learning algorithms as tools for
student success prediction
Assoc. Prof. Dijana Oreški, PhD
University of Zagreb
Faculty of Organization and Informatics
Intro
• This work has been supported by Croatian Science
Foundation under the project UIP-2020-02-6312.
 SIMON – Intelligent system for automatic selection of machine
learning algorithm in social sciences
• Lab Louise
 Laboratory for data mining and intelligent systems
 louise.foi.hr
Intro
• “If you torture data long enough they will confess at
the end.”
Ronald Coase
Agenda
• Introduction
 Education data & WHY?
 machine learning algorithms
• Research motivation
• Research methodology HOW?
 CRISP DM standard
• Research results WHAT?
 Model evaluation
 Model interpretation
• Conclusion
Agenda
• Introduction
 Education data & WHY?
 machine learning algorithms
• Research motivation
• Research methodology HOW?
 CRISP DM standard
• Research results WHAT?
 Model evaluation
 Model interpretation
• Conclusion
Introduction
• Huge number of machine learning algorithms
applications in a broad spectrum of domains.
 Crucial role in harnessing the power of the vast amount of data
we produce daily in the digital age.
• The application of algorithms is complex, iterative and
time-consuming.
 There is a need to automate the selection of algorithms for
models development.
• Which algorithm is best to used in a specific situation,
in a particular domain, at a particular dataset?
Research motivation
Research motivation
Education
data
Supervised
machine
learning
algorithms
Agenda
• Introduction
 Education data & WHY?
 machine learning algorithms
• Research motivation
• Research methodology HOW?
 CRISP DM standard
• Research results WHAT?
 Model evaluation
 Model interpretation
• Conclusion
CRISP DM standard
Data
preparation
Data
understanding
Evaluation
Modelling
Data
Domain
understanding
Deployment
Research papers
• Kliček, B.; Oreški, D.; Divjak, B., Determining individual learning
strategies for students in higher education using neural networks,
International Journal of Arts and Sciences.
• Oreški, D; Konecki, M; Pihir, I: Predictive Modelling of Academic
Performance by Means of Bayesian Networks, 47th International
Scientific Conference on Economic and Social Development.
• Oreški, D; Pihir, I; Konecki, M., CRISP-DM process model in
educational setting, 20th International Scientific Conference on
Economic and Social Development
Research papers
• Oreški, D; Konecki, M; Milić, L., Estimating profile of successful IT
student: data mining approach, MIPRO 2017 - 40th International
Convention Proceedings
• Kovač, R; Oreški, D., Educational Data Driven Decision Making:
Early Identification of Students at Risk by Means of Machine
Learning, Proceedings of CECIIS 2018 /
• Oreški, D.; Hajdin, G., Exploring differences in predictors of
academic success between different generations of students,
EDULEARN19 Proceedings, 2019.
Research papers
• Oreški, D., Hajdin, G. Development and comparison of predictive
models based on learning management system data // WSEAS
TRANSACTIONS on INFORMATION SCIENCE and APPLICATIONS,
2019
• Oreški, D.; Hajdin, G., A Comparative Study of Machine Learning
Approaches on Learning Management System Data, 2019
Proceedings - 3rd International Conference on Control, Artificial
Intelligence, Robotics & Optimization
• Filipović, D.; Balaban, I.; Oreški, D., Cluster analysis of students’
activities from logs and their success in self-assessment tests,
Proceedings of CECIIS 2018
• Oreški, D.; Kadoić, N., Analysis of ICT students' LMS engagement
and sucess, International Scientific Conference on Economic and
Social Development, 2018.
Domain understanding
• Research goals:
 To determine whether data from different sources (surveys, e-
learning systems...) can be a good basis for creating predictive
models of academic success.
 To determine which variables are the best predictors of
academic success.
 To determine whether predictors of success change over time.
Domain understanding
• The improvement of the educational system and the
achievement of students optimal learning requires the
data collection and analysis.
 Recent papers deal with this topic from the perspective of:
 (i) the various academic and non-academic factors involved
in the data,
 (ii) the research methodology used in data analysis:
previously focused on advanced statistical approaches,
nowadays on machine learning approaches,
 iii) accuracy and reliability of developed predictive models.
Data understanding
• Data sources:
 Survey,
 Learning management system data,
 YouTube analytics.
Data understanding
• Data sources:
 Survey,
 Learning management system data,
 YouTube analytics.
Data understanding
Students through generations
Data understanding
Students by entrance exam results
Bottom 10%-30% Middle Top 10%
Data understanding
First grade at the Faculty
Data understanding
I manage time well
Completely Disagree Neither agree Agree Completely
disagree or disagree agree
Data understanding
I see myself as responsible person
Completely Disagree Neither agree Agree Completely
disagree or disagree agree
Data understanding
I find teamwork useful
Completely Disagree Neither agree Agree Completely
disagree or disagree agree
Data understanding
I have prepared for the classes
Completely Disagree Neither agree Agree Completely
disagree or disagree agree
Data understanding
• Data sources:
 Survey,
 Learning management system data,
 YouTube analytics.
Data understanding
Data understanding
Data understanding
Data understanding
Data understanding
• Data sources:
 Survey,
 Learning management system data,
 YouTube analytics.
Data understanding
Variable Variable Correlation
Video duration Percentage of video views -0,78
Variable Variable Correlation
Complexity
Percentage of video
views
-0,35
Modelling
• Information based machine learning
 Decision tree
• Similarity based machine learning
 K-nearest neighbours
 “When I see a bird that walks like a duck and swims like a duck
and quacks like a duck, I call that bird a duck.” James W. Riley
• Error based machine learning
 Neural networks
 “Success is stumbling from failure to failure with no loss of
enthusiasm.” Winston Churchill
• Probability based machine learning
 Bayesian networks
 “When my information changes, I alter my conclusions. What
do you do, sir?” John Maynard Keynes
Agenda
• Introduction
 Education data & WHY?
 machine learning algorithms
• Research motivation
• Research methodology HOW?
 CRISP DM standard
• Research results WHAT?
 Model evaluation
 Model interpretation
• Conclusion
Research results
rang A rang B rang C
Highschool grade
average 1 1 4
Lecture attendance 2 4 10
First grade at the
Faculty 3 3 3
I manage my time
well 4 15 13
Entrance exam
results 5 2 1
I find myself as
responsible person 8 10 5
Seminars attendance 9 11 7
I have prepared for
the classes 12 13 12
I find teamwork
useful 15 8 9
Gender 16 7 16
Research results
• Strong positive correlation between predictors of academic success
in Generations B and C(r=0.652941176, p<0,01).
• Correlations in predictors between generations A and B
(r=0.370588235, p<0,01), A and C(r=0.388235294, p<0,01) are
smaller.
• Conclusion:
 Predictors of student success change over time, but only when
there are significant changes in the education system.
Research results
• Female students are more active on the e-learning
system and complete the course more successfully than
male colleagues.
• Activity on the e-learning system is a significant
predictor of student success.
 Students were most active during the weeks of the colloquium,
and especially the day before the colloquium.
 Students can be characterized as "last minute" students,
because they fulfill their obligations as late as possible in terms
of the deadline.
 They are active in the "late" hours.
Conclusion
• Machine learning algorithms provide accurate and
reliable predictive models.
• However, results are not perfect:
 Predicting students at risk will always suffer from classification
errors - false positives and false negatives.
 The error affects the allocation of available resources.
 Potentially negative effects on the individual.
Conclusion
• To determine whether data from different sources
(surveys, e-learning systems...) can be a good basis for
creating predictive models of academic success.
 Yes! Integration contributes to successful prediction.
• To determine which variables are the best predictors of
academic success.
 First grade at the faculty, previous knowledge..
 LMS activity..
• To determine whether predictors of success change
over time.
 Change according to change in educational system.
Thank you!

Weitere ähnliche Inhalte

Ähnlich wie [DSC Europe 22] Machine learning algorithms as tools for student success prediction - Dijana Oreski

NCME Big Data in Education
NCME Big Data  in EducationNCME Big Data  in Education
NCME Big Data in Education
Philip Piety
 
EDUCA Leveraging Analytics FINAL
EDUCA Leveraging Analytics FINALEDUCA Leveraging Analytics FINAL
EDUCA Leveraging Analytics FINAL
Ellen Wagner
 
Learning analytics overview: Building evidence based practice
Learning analytics overview: Building evidence based practiceLearning analytics overview: Building evidence based practice
Learning analytics overview: Building evidence based practice
Shane Dawson
 

Ähnlich wie [DSC Europe 22] Machine learning algorithms as tools for student success prediction - Dijana Oreski (20)

Krakow presentation speak_appsmngm_final
Krakow presentation speak_appsmngm_finalKrakow presentation speak_appsmngm_final
Krakow presentation speak_appsmngm_final
 
NCME Big Data in Education
NCME Big Data  in EducationNCME Big Data  in Education
NCME Big Data in Education
 
Learning Analytics: New thinking supporting educational research
Learning Analytics: New thinking supporting educational researchLearning Analytics: New thinking supporting educational research
Learning Analytics: New thinking supporting educational research
 
Ba education
Ba educationBa education
Ba education
 
Recommendation of Data Mining Technique in Higher Education Prof. Priya Thaka...
Recommendation of Data Mining Technique in Higher Education Prof. Priya Thaka...Recommendation of Data Mining Technique in Higher Education Prof. Priya Thaka...
Recommendation of Data Mining Technique in Higher Education Prof. Priya Thaka...
 
Analytics in Action - Education
Analytics in Action - EducationAnalytics in Action - Education
Analytics in Action - Education
 
Empowering the Instructor with Learning Analytics
Empowering the Instructor with Learning AnalyticsEmpowering the Instructor with Learning Analytics
Empowering the Instructor with Learning Analytics
 
Education data mining presentation
Education data mining presentationEducation data mining presentation
Education data mining presentation
 
27_06_2019 Wolfgang Greller, from University of Teacher Education (Viena), on...
27_06_2019 Wolfgang Greller, from University of Teacher Education (Viena), on...27_06_2019 Wolfgang Greller, from University of Teacher Education (Viena), on...
27_06_2019 Wolfgang Greller, from University of Teacher Education (Viena), on...
 
Learning Analytics for Self-Regulated Learning (2019)
Learning Analytics for Self-Regulated Learning (2019)Learning Analytics for Self-Regulated Learning (2019)
Learning Analytics for Self-Regulated Learning (2019)
 
Mehrnoosh vahdat workshop-data sharing 2014
Mehrnoosh vahdat  workshop-data sharing 2014Mehrnoosh vahdat  workshop-data sharing 2014
Mehrnoosh vahdat workshop-data sharing 2014
 
Learning Analytics In Higher Education: Struggles & Successes (Part 2)
Learning Analytics In Higher Education: Struggles & Successes (Part 2)Learning Analytics In Higher Education: Struggles & Successes (Part 2)
Learning Analytics In Higher Education: Struggles & Successes (Part 2)
 
EDUCA Leveraging Analytics FINAL
EDUCA Leveraging Analytics FINALEDUCA Leveraging Analytics FINAL
EDUCA Leveraging Analytics FINAL
 
Tracking learners digital experience: the benefits and impacts
Tracking learners digital experience: the benefits and impactsTracking learners digital experience: the benefits and impacts
Tracking learners digital experience: the benefits and impacts
 
Learning analytics overview: Building evidence based practice
Learning analytics overview: Building evidence based practiceLearning analytics overview: Building evidence based practice
Learning analytics overview: Building evidence based practice
 
Jisc learning analytics service updates
Jisc learning analytics service updatesJisc learning analytics service updates
Jisc learning analytics service updates
 
Learning Analytics
Learning AnalyticsLearning Analytics
Learning Analytics
 
Mseit advisory mtgoctober2013
Mseit advisory mtgoctober2013Mseit advisory mtgoctober2013
Mseit advisory mtgoctober2013
 
Ethical challenges for learning analytics
Ethical challenges for learning analyticsEthical challenges for learning analytics
Ethical challenges for learning analytics
 
Learning Analytics
Learning AnalyticsLearning Analytics
Learning Analytics
 

Mehr von DataScienceConferenc1

[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf
[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf
[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf
DataScienceConferenc1
 
[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf
[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf
[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf
DataScienceConferenc1
 
[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx
[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx
[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx
DataScienceConferenc1
 

Mehr von DataScienceConferenc1 (20)

[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf
[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf
[DSC MENA 24] Mostafa_Essa_-_Ai_and_cloud.pdf
 
[DSC MENA 24] Yasser_El_Bendary - How NLP & LLMs model can excel in comprehen...
[DSC MENA 24] Yasser_El_Bendary - How NLP & LLMs model can excel in comprehen...[DSC MENA 24] Yasser_El_Bendary - How NLP & LLMs model can excel in comprehen...
[DSC MENA 24] Yasser_El_Bendary - How NLP & LLMs model can excel in comprehen...
 
[DSC MENA 24] Medhat_Kandil - Empowering Egypt's AI & Biotechnology Scenes.pdf
[DSC MENA 24] Medhat_Kandil - Empowering Egypt's AI & Biotechnology Scenes.pdf[DSC MENA 24] Medhat_Kandil - Empowering Egypt's AI & Biotechnology Scenes.pdf
[DSC MENA 24] Medhat_Kandil - Empowering Egypt's AI & Biotechnology Scenes.pdf
 
[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf
[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf
[DSC MENA 24] Youssef_Kamal - Data governance and quality.pdf
 
[DSC MENA 24] Abdelrahman_Ghallab_-_Data_Product_mgmt.pdf
[DSC MENA 24] Abdelrahman_Ghallab_-_Data_Product_mgmt.pdf[DSC MENA 24] Abdelrahman_Ghallab_-_Data_Product_mgmt.pdf
[DSC MENA 24] Abdelrahman_Ghallab_-_Data_Product_mgmt.pdf
 
[DSC MENA 24] Asmaa_Eltaher_-_Innovation_Beyond_Brainstorming.pptx
[DSC MENA 24] Asmaa_Eltaher_-_Innovation_Beyond_Brainstorming.pptx[DSC MENA 24] Asmaa_Eltaher_-_Innovation_Beyond_Brainstorming.pptx
[DSC MENA 24] Asmaa_Eltaher_-_Innovation_Beyond_Brainstorming.pptx
 
[DSC MENA 24] Muhammad_Ezzat_-_Sustianable_Growth_Empowerment.pdf
[DSC MENA 24] Muhammad_Ezzat_-_Sustianable_Growth_Empowerment.pdf[DSC MENA 24] Muhammad_Ezzat_-_Sustianable_Growth_Empowerment.pdf
[DSC MENA 24] Muhammad_Ezzat_-_Sustianable_Growth_Empowerment.pdf
 
[DSC MENA 24] Basma_Rady_-_Building_a_Data_Driven_Culture_in_Your_Organizatio...
[DSC MENA 24] Basma_Rady_-_Building_a_Data_Driven_Culture_in_Your_Organizatio...[DSC MENA 24] Basma_Rady_-_Building_a_Data_Driven_Culture_in_Your_Organizatio...
[DSC MENA 24] Basma_Rady_-_Building_a_Data_Driven_Culture_in_Your_Organizatio...
 
[DSC MENA 24] Ahmed_Muselhy_-_Unveiling-the-Secrets-of-AI-in-Hiring.pdf
[DSC MENA 24] Ahmed_Muselhy_-_Unveiling-the-Secrets-of-AI-in-Hiring.pdf[DSC MENA 24] Ahmed_Muselhy_-_Unveiling-the-Secrets-of-AI-in-Hiring.pdf
[DSC MENA 24] Ahmed_Muselhy_-_Unveiling-the-Secrets-of-AI-in-Hiring.pdf
 
[DSC MENA 24] Ziad_Diab_-_Data-Driven_Disruption_-_The_Role_of_Data_Strategy_...
[DSC MENA 24] Ziad_Diab_-_Data-Driven_Disruption_-_The_Role_of_Data_Strategy_...[DSC MENA 24] Ziad_Diab_-_Data-Driven_Disruption_-_The_Role_of_Data_Strategy_...
[DSC MENA 24] Ziad_Diab_-_Data-Driven_Disruption_-_The_Role_of_Data_Strategy_...
 
[DSC MENA 24] Mohammad_Essam_- Leveraging Scene Graphs for Generative AI and ...
[DSC MENA 24] Mohammad_Essam_- Leveraging Scene Graphs for Generative AI and ...[DSC MENA 24] Mohammad_Essam_- Leveraging Scene Graphs for Generative AI and ...
[DSC MENA 24] Mohammad_Essam_- Leveraging Scene Graphs for Generative AI and ...
 
[DSC MENA 24] Ahmed_Fahmy - Navigating the Future.pdf
[DSC MENA 24] Ahmed_Fahmy - Navigating the Future.pdf[DSC MENA 24] Ahmed_Fahmy - Navigating the Future.pdf
[DSC MENA 24] Ahmed_Fahmy - Navigating the Future.pdf
 
[DSC MENA 24] Hany_Saad_Gheit_-_Azure_OpenAI_service.pptx
[DSC MENA 24] Hany_Saad_Gheit_-_Azure_OpenAI_service.pptx[DSC MENA 24] Hany_Saad_Gheit_-_Azure_OpenAI_service.pptx
[DSC MENA 24] Hany_Saad_Gheit_-_Azure_OpenAI_service.pptx
 
[DSC MENA 24] Nezar_El_Kady_-_From_Turing_to_Transformers__Navigating_the_AI_...
[DSC MENA 24] Nezar_El_Kady_-_From_Turing_to_Transformers__Navigating_the_AI_...[DSC MENA 24] Nezar_El_Kady_-_From_Turing_to_Transformers__Navigating_the_AI_...
[DSC MENA 24] Nezar_El_Kady_-_From_Turing_to_Transformers__Navigating_the_AI_...
 
[DSC MENA 24] Amira_Abdelaziz_-_AI_in_Financial_Services.pptx
[DSC MENA 24] Amira_Abdelaziz_-_AI_in_Financial_Services.pptx[DSC MENA 24] Amira_Abdelaziz_-_AI_in_Financial_Services.pptx
[DSC MENA 24] Amira_Abdelaziz_-_AI_in_Financial_Services.pptx
 
[DSC MENA 24] Omar_Ossama - My Journey from the Field of Oil & Gas, to the Ex...
[DSC MENA 24] Omar_Ossama - My Journey from the Field of Oil & Gas, to the Ex...[DSC MENA 24] Omar_Ossama - My Journey from the Field of Oil & Gas, to the Ex...
[DSC MENA 24] Omar_Ossama - My Journey from the Field of Oil & Gas, to the Ex...
 
[DSC MENA 24] Ramy_Agieb_-_Advancements_in_Artificial_Intelligence_for_Cybers...
[DSC MENA 24] Ramy_Agieb_-_Advancements_in_Artificial_Intelligence_for_Cybers...[DSC MENA 24] Ramy_Agieb_-_Advancements_in_Artificial_Intelligence_for_Cybers...
[DSC MENA 24] Ramy_Agieb_-_Advancements_in_Artificial_Intelligence_for_Cybers...
 
[DSC MENA 24] Sohaila_Diab_-_Lets_Talk_Gen_AI_Presentation.pptx
[DSC MENA 24] Sohaila_Diab_-_Lets_Talk_Gen_AI_Presentation.pptx[DSC MENA 24] Sohaila_Diab_-_Lets_Talk_Gen_AI_Presentation.pptx
[DSC MENA 24] Sohaila_Diab_-_Lets_Talk_Gen_AI_Presentation.pptx
 
[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx
[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx
[DSC MENA 24] Amal_Elgammal_-_QUALITOP_presentation.pptx
 
[DSC MENA 24] Abdelrahman_Sleem_-_AI_For_Marketing_DSC.pdf
[DSC MENA 24] Abdelrahman_Sleem_-_AI_For_Marketing_DSC.pdf[DSC MENA 24] Abdelrahman_Sleem_-_AI_For_Marketing_DSC.pdf
[DSC MENA 24] Abdelrahman_Sleem_-_AI_For_Marketing_DSC.pdf
 

Kürzlich hochgeladen

Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
gajnagarg
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
gajnagarg
 
Computer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdfComputer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdf
SayantanBiswas37
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
HyderabadDolls
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Klinik kandungan
 

Kürzlich hochgeladen (20)

Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book nowVadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
Vadodara 💋 Call Girl 7737669865 Call Girls in Vadodara Escort service book now
 
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
High Profile Call Girls Service in Jalore { 9332606886 } VVIP NISHA Call Girl...
 
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Statistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbersStatistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbers
 
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With OrangePredicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubai
 
Computer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdfComputer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdf
 
Ranking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRanking and Scoring Exercises for Research
Ranking and Scoring Exercises for Research
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham Ware
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
 

[DSC Europe 22] Machine learning algorithms as tools for student success prediction - Dijana Oreski

  • 1. Machine learning algorithms as tools for student success prediction Assoc. Prof. Dijana Oreški, PhD University of Zagreb Faculty of Organization and Informatics
  • 2. Intro • This work has been supported by Croatian Science Foundation under the project UIP-2020-02-6312.  SIMON – Intelligent system for automatic selection of machine learning algorithm in social sciences • Lab Louise  Laboratory for data mining and intelligent systems  louise.foi.hr
  • 3. Intro • “If you torture data long enough they will confess at the end.” Ronald Coase
  • 4. Agenda • Introduction  Education data & WHY?  machine learning algorithms • Research motivation • Research methodology HOW?  CRISP DM standard • Research results WHAT?  Model evaluation  Model interpretation • Conclusion
  • 5. Agenda • Introduction  Education data & WHY?  machine learning algorithms • Research motivation • Research methodology HOW?  CRISP DM standard • Research results WHAT?  Model evaluation  Model interpretation • Conclusion
  • 6. Introduction • Huge number of machine learning algorithms applications in a broad spectrum of domains.  Crucial role in harnessing the power of the vast amount of data we produce daily in the digital age. • The application of algorithms is complex, iterative and time-consuming.  There is a need to automate the selection of algorithms for models development. • Which algorithm is best to used in a specific situation, in a particular domain, at a particular dataset?
  • 9. Agenda • Introduction  Education data & WHY?  machine learning algorithms • Research motivation • Research methodology HOW?  CRISP DM standard • Research results WHAT?  Model evaluation  Model interpretation • Conclusion
  • 11. Research papers • Kliček, B.; Oreški, D.; Divjak, B., Determining individual learning strategies for students in higher education using neural networks, International Journal of Arts and Sciences. • Oreški, D; Konecki, M; Pihir, I: Predictive Modelling of Academic Performance by Means of Bayesian Networks, 47th International Scientific Conference on Economic and Social Development. • Oreški, D; Pihir, I; Konecki, M., CRISP-DM process model in educational setting, 20th International Scientific Conference on Economic and Social Development
  • 12. Research papers • Oreški, D; Konecki, M; Milić, L., Estimating profile of successful IT student: data mining approach, MIPRO 2017 - 40th International Convention Proceedings • Kovač, R; Oreški, D., Educational Data Driven Decision Making: Early Identification of Students at Risk by Means of Machine Learning, Proceedings of CECIIS 2018 / • Oreški, D.; Hajdin, G., Exploring differences in predictors of academic success between different generations of students, EDULEARN19 Proceedings, 2019.
  • 13. Research papers • Oreški, D., Hajdin, G. Development and comparison of predictive models based on learning management system data // WSEAS TRANSACTIONS on INFORMATION SCIENCE and APPLICATIONS, 2019 • Oreški, D.; Hajdin, G., A Comparative Study of Machine Learning Approaches on Learning Management System Data, 2019 Proceedings - 3rd International Conference on Control, Artificial Intelligence, Robotics & Optimization • Filipović, D.; Balaban, I.; Oreški, D., Cluster analysis of students’ activities from logs and their success in self-assessment tests, Proceedings of CECIIS 2018 • Oreški, D.; Kadoić, N., Analysis of ICT students' LMS engagement and sucess, International Scientific Conference on Economic and Social Development, 2018.
  • 14. Domain understanding • Research goals:  To determine whether data from different sources (surveys, e- learning systems...) can be a good basis for creating predictive models of academic success.  To determine which variables are the best predictors of academic success.  To determine whether predictors of success change over time.
  • 15. Domain understanding • The improvement of the educational system and the achievement of students optimal learning requires the data collection and analysis.  Recent papers deal with this topic from the perspective of:  (i) the various academic and non-academic factors involved in the data,  (ii) the research methodology used in data analysis: previously focused on advanced statistical approaches, nowadays on machine learning approaches,  iii) accuracy and reliability of developed predictive models.
  • 16. Data understanding • Data sources:  Survey,  Learning management system data,  YouTube analytics.
  • 17. Data understanding • Data sources:  Survey,  Learning management system data,  YouTube analytics.
  • 19. Data understanding Students by entrance exam results Bottom 10%-30% Middle Top 10%
  • 21. Data understanding I manage time well Completely Disagree Neither agree Agree Completely disagree or disagree agree
  • 22. Data understanding I see myself as responsible person Completely Disagree Neither agree Agree Completely disagree or disagree agree
  • 23. Data understanding I find teamwork useful Completely Disagree Neither agree Agree Completely disagree or disagree agree
  • 24. Data understanding I have prepared for the classes Completely Disagree Neither agree Agree Completely disagree or disagree agree
  • 25. Data understanding • Data sources:  Survey,  Learning management system data,  YouTube analytics.
  • 30. Data understanding • Data sources:  Survey,  Learning management system data,  YouTube analytics.
  • 31. Data understanding Variable Variable Correlation Video duration Percentage of video views -0,78 Variable Variable Correlation Complexity Percentage of video views -0,35
  • 32. Modelling • Information based machine learning  Decision tree • Similarity based machine learning  K-nearest neighbours  “When I see a bird that walks like a duck and swims like a duck and quacks like a duck, I call that bird a duck.” James W. Riley • Error based machine learning  Neural networks  “Success is stumbling from failure to failure with no loss of enthusiasm.” Winston Churchill • Probability based machine learning  Bayesian networks  “When my information changes, I alter my conclusions. What do you do, sir?” John Maynard Keynes
  • 33. Agenda • Introduction  Education data & WHY?  machine learning algorithms • Research motivation • Research methodology HOW?  CRISP DM standard • Research results WHAT?  Model evaluation  Model interpretation • Conclusion
  • 34. Research results rang A rang B rang C Highschool grade average 1 1 4 Lecture attendance 2 4 10 First grade at the Faculty 3 3 3 I manage my time well 4 15 13 Entrance exam results 5 2 1 I find myself as responsible person 8 10 5 Seminars attendance 9 11 7 I have prepared for the classes 12 13 12 I find teamwork useful 15 8 9 Gender 16 7 16
  • 35. Research results • Strong positive correlation between predictors of academic success in Generations B and C(r=0.652941176, p<0,01). • Correlations in predictors between generations A and B (r=0.370588235, p<0,01), A and C(r=0.388235294, p<0,01) are smaller. • Conclusion:  Predictors of student success change over time, but only when there are significant changes in the education system.
  • 36. Research results • Female students are more active on the e-learning system and complete the course more successfully than male colleagues. • Activity on the e-learning system is a significant predictor of student success.  Students were most active during the weeks of the colloquium, and especially the day before the colloquium.  Students can be characterized as "last minute" students, because they fulfill their obligations as late as possible in terms of the deadline.  They are active in the "late" hours.
  • 37. Conclusion • Machine learning algorithms provide accurate and reliable predictive models. • However, results are not perfect:  Predicting students at risk will always suffer from classification errors - false positives and false negatives.  The error affects the allocation of available resources.  Potentially negative effects on the individual.
  • 38. Conclusion • To determine whether data from different sources (surveys, e-learning systems...) can be a good basis for creating predictive models of academic success.  Yes! Integration contributes to successful prediction. • To determine which variables are the best predictors of academic success.  First grade at the faculty, previous knowledge..  LMS activity.. • To determine whether predictors of success change over time.  Change according to change in educational system.