Customer service improvement based on payment behavior electricity bill analysis using data mining approaches

Name: Parinya Khansong

keyword: Electricity bills

; Customer segmentation

; Clustering

; Data mining

; Predictive model

Abstract: Thailand Provincial Electricity Authority (PEA) has 19.36 million residential customers and approximately 73% of them have late or unpaid electricity payments. This causes several problems including reduction of PEA's income. Therefore, we aim to classify customers and to find data mining algorithms that predict classes of electricity payment behaviors of residential customers in order to improve customer service, to design marketing campaigns, to improve customer satisfaction and to reduce the number of late or unpaid payment of electricity bills. In this research, the data set consists of payment behaviors and demographic characteristics of customers, which are gathered from the questionnaire responses of 1,079 walk-in customers. The class prediction process is divided into two main parts: (a) clustering classes of customers by using Gaussian mixture model (GMM), agglomerative hierarchical clustering (AHC), and k-means algorithm. We evaluated those algorithms using the Davies-Bouldin index (DBI), and then choose clustering algorithm that gives the best score as the clustering model. (b) Using data mining algorithms to predict a class of a given customer. We performed experiments that compare five data mining algorithms, which are logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), and extreme gradient boosted (XGBoost). These algorithms are evaluated with a confusion matrix to select the best algorithm. Our results showed that the random forest algorithm is a good choice for customer class prediction, and it can be used to develop appropriate strategies to increase satisfaction of customers and revenue of PEA. This research is useful for organizations electricity and want to understand the electricity bill payment behavior of their customers. Collectively, it leads to the development of appropriate strategies to increase satisfaction of customers and profit

Thammasat University. Thammasat University Library

Address: BANGKOK

Email: preserv@tu.ac.th

Name: Seksan Laitrakun

Role: advisor

Name: Jessada Karnjana

Role: co-advisor

Created: 2021

Modified: 2023-02-20

Issued: 2023-02-20

วิทยานิพนธ์/Thesis

application/pdf

DOI: 10.14457/TU.the.2021.75

eng

DegreeName: Master of Engineering

Level: Master's Degree

Descipline: Engineering Technology

Grantor: Thammasat University

©copyrights Thammasat University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	10584parinya.pdf	2.2 MB	1	2024-05-20 10:53:42

ใช้เวลา

0.024843 วินาที