Implementing KNIME Analytical Platform for visualizing data in educational context
Make, Gjergji (2018)
Make, Gjergji
Haaga-Helia ammattikorkeakoulu
2018
All rights reserved
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2018121221046
https://urn.fi/URN:NBN:fi:amk-2018121221046
Tiivistelmä
Big Data is playing a big role in technology Industry nowadays. Decision making is becoming easier throughout Data mining and Machine learning. There is vast amount of data provided by human beings’ behaviour and technology usage. With the right interpretation on the proper context these data are far more than useful to predict and make correct decisions for better performance.
This thesis paper will be focusing on implementing Data Mining (DM), Machine Learning (ML) and Data Analytics to BITe Program students of Haaga-Helia University. Dataset used in this project are collected using the study of (NIEMIVIRTA, 2002) on eight scales of motivational factors. Results of this questionnaire are constructed, transformed and visualized using KNIME Analytical Platform. Using the same platform data mining will be implemented to this dataset for understanding and finding hidden truths for increasing student performance.
CRISP-DM methodology is used to develop this project. There will be 5 main sub-chapters explaining step by step process of how the results are achieved:
1. Data understanding
2. Data preparation
3. Modeling
4. Evaluation
5. Deployment
To summarize, this thesis will give the reader a clear structure of the KNIME project, important student behaviour data visualization and simple prediction of fear of failure motivation factor.
This thesis paper will be focusing on implementing Data Mining (DM), Machine Learning (ML) and Data Analytics to BITe Program students of Haaga-Helia University. Dataset used in this project are collected using the study of (NIEMIVIRTA, 2002) on eight scales of motivational factors. Results of this questionnaire are constructed, transformed and visualized using KNIME Analytical Platform. Using the same platform data mining will be implemented to this dataset for understanding and finding hidden truths for increasing student performance.
CRISP-DM methodology is used to develop this project. There will be 5 main sub-chapters explaining step by step process of how the results are achieved:
1. Data understanding
2. Data preparation
3. Modeling
4. Evaluation
5. Deployment
To summarize, this thesis will give the reader a clear structure of the KNIME project, important student behaviour data visualization and simple prediction of fear of failure motivation factor.