Authors :
Terrence Njiru Kananda; Henry Mwangi
Volume/Issue :
Volume 8 - 2023, Issue 3 - March
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://bit.ly/3lYk5uL
DOI :
https://doi.org/10.5281/zenodo.7793063
Abstract :
- Stakeholders in Kenyan education are
concerned about student performance. Data mining has
emerged as an alternate method for education
stakeholders to employ in making decisions about
student performance in their final year exam. Kenya's
education sector provides a wealth of statistical data that
might provide vital information about students.
Information and communication technology collects and
compiles low-cost data that can be used to forecast
student performance. However, no meaningful
information is extracted from this data by Kenyan
educational institutions. In this paper, we propose and
develop a prediction model for forecasting Kenya
secondary school learner performance utilizing prior
performance data from students, which will be
transformed and cleaned before being used in training
and testing the model. Our model employs data mining
techniques to improve forecast accuracy. We will present
the model theoretical framework, conceptual
framework, and outcomes.
Keywords :
DM - Data Mining, EDM – Educational Data Mining, KCPE – Kenya Certificate of Primary Education, KCSE – Kenya Certificate of Secondary Education
- Stakeholders in Kenyan education are
concerned about student performance. Data mining has
emerged as an alternate method for education
stakeholders to employ in making decisions about
student performance in their final year exam. Kenya's
education sector provides a wealth of statistical data that
might provide vital information about students.
Information and communication technology collects and
compiles low-cost data that can be used to forecast
student performance. However, no meaningful
information is extracted from this data by Kenyan
educational institutions. In this paper, we propose and
develop a prediction model for forecasting Kenya
secondary school learner performance utilizing prior
performance data from students, which will be
transformed and cleaned before being used in training
and testing the model. Our model employs data mining
techniques to improve forecast accuracy. We will present
the model theoretical framework, conceptual
framework, and outcomes.
Keywords :
DM - Data Mining, EDM – Educational Data Mining, KCPE – Kenya Certificate of Primary Education, KCSE – Kenya Certificate of Secondary Education
