Customer segmentation of car retails using regularized logistic regression compared with K means clustering

Nowadays, the competitors for car retails are increasing very rapidly and every retailer should know their customers’ expectations and try to reach them. This paper represents a customer segmentation model which helps them to group the customers with the same market characteristics. Materials and Me...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vagalla, Upendra Reddy, Selvaraj, John Justin Thangaraj
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Nowadays, the competitors for car retails are increasing very rapidly and every retailer should know their customers’ expectations and try to reach them. This paper represents a customer segmentation model which helps them to group the customers with the same market characteristics. Materials and MethodsThe study contains 2 groups i.e, the K Means clustering model is developed in the first group and Regularized Logistic Regression model, a supervised machine learning algorithm is developed in the second group. Each group has a sample size of 200 and the study parameters include alpha value 0.05, beta value 0.2, and the power value 0.8. The accuracies of each model are compared with others for different sample sizes. Result: This paper is an attempt to improve the accuracy of customer segmentation using the Regularized Logistic Regression(RLR), a supervised predictive machine learning algorithm. The L2 or Ridge Regularization avoids the overfitting of the data. The proposed model has an improved accuracy of 87.5 % with p < 0.05 in segmenting customers than the existing model of 85 %. It helps the car retail entrepreneurship be more reliable and robust. The outcomes of the proposed model are compared with the K Means Clustering algorithm and the proposed model confirms to have higher accuracy than the K Means Clustering algorithm.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0118059