Publication Date: 2023/07/14
Abstract: The rise of numerous competitors and entrepreneurs which has led to a great deal of competition among businesses, compelling them to seek out new customers while retaining their existing ones. Consequently, the importance of delivering exceptional customer service has become crucial, regardless of a business's size or scale [2]. Moreover, understanding the unique needs of each customer is paramount to providing targeted support and developing personalized customer service strategies. This level of comprehension can be achieved through the implementation of a well- structured customer service framework, as different customer segments often share similar market characteristics [5]. To tackle the challenges posed by a large customer base, the integration machine learning has gained traction, surpassing traditional market analytics methods that tend to falter under such circumstances. This paper adopts the k-means clustering algorithm to address this issue [8]. The implementation of the k- Means algorithm, facilitated by the Sklearn library (refer to the Appendix), involves training a program using a dataset comprising 100 patterns and two factors
Keywords: data mining; machine learning; customer segment; k-Mean algorithm; sklearn; extrapolation.
DOI: https://doi.org/10.5281/zenodo.8146941
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23JUN2162.pdf
REFERENCES