Correlation model in the adoption of E-payment services: A machine learning approach
The purpose of this study was to understand the highly correlated factors that influence user intention to adopt e-payment into their daily lives. The research framework incorporates the 4 main constructs of the UTAUT model and additional determinants of the extended UTAUT model to model the relatio...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/4670/1/fyp_CS_2022_TXE.pdf http://eprints.utar.edu.my/4670/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The purpose of this study was to understand the highly correlated factors that influence user intention to adopt e-payment into their daily lives. The research framework incorporates the 4 main constructs of the UTAUT model and additional determinants of the extended UTAUT model to model the relationship. Previous research has shown that the UTAUT model is able to model the relationship of factors that influence user intention to adopt e-payment. To analyse results, a questionnaire was developed based on the UTAUT model, and was distributed among university graduates, researchers, and students. In total, 286 samples were recorded and analysed. Previously, identifying highly correlated user behaviours was done through a lot of statistical research and hypothesis testing. The main goal of the project is to automate this process, by using machine learning to identify the important features. To extract highly correlated features, several pairwise correlation methods were used, such as Pearson’s Correlation, and Spearman’s Correlation. Then, by using Correlation Based Feature selection algorithm, we select the best subset of features out of the highly correlated features to do predictive modelling. This is a novel method, as we do not need to rely on statistical analysis, rather we can automate the process of identifying important features using machine learning models. The end goal of the project is to develop a model that identifies the important features that affect user intention to adopt e-payment. |
|---|