Unsupervised Feature Selection Approach for Smartwatches

Traditional feature selection methods can be time-consuming and labor-intensive, especially with large datasets. This study’s unsupervised feature selection approach can automate the process and help identify important features preferred by a particular segment of users. The unsupervised feature selection method is applied for smartwatches. Smartwatches continue to gain popularity. It is important to understand which features are most important to users to design and develop smartwatches that are more engaging, user-friendly, and meet the needs and preferences of their target audience. The rapid pace of technological innovation in the smartwatch industry means that new features and functionalities are constantly being developed. Multi-cluster feature selection, Laplacian score, and unsupervised spectral feature are used. Conjoint analysis is done on the most common features in all three selection methods. The unsupervised feature selection technique is used for identifying the relevant and important features of new smartwatch users. The practical implication of the research is in the application of the technique in the new product design of smartwatches. The result of the study also informs smartwatch manufacturers and developers on the features they need to prioritize and invest in. This can ultimately result in better and more user-friendly smartwatches and a good overall experience for the user.