Predicting Firms' Performances in Customer Complaint Management Using Machine Learning Techniques


Peker S.

4th International Conference on Intelligent and Fuzzy Systems (INFUS), Bornova, Turkey, 19 - 21 July 2022, vol.505, pp.280-287 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 505
  • Doi Number: 10.1007/978-3-031-09176-6_33
  • City: Bornova
  • Country: Turkey
  • Page Numbers: pp.280-287
  • Keywords: Data mining, Machine learning, Business intelligence, CRM analytics, Data-driven CRM, DATA MINING TECHNIQUES, HYBRID APPROACH, INDUSTRY, CHURN
  • Yıldız Technical University Affiliated: No

Abstract

With the globalization and more intense increasing competition, customer relationship management (CRM) is an important issue in today's business. In this manner, managing customer complaints which is a critical part of CRM presents firms with an is an opportunity to make long-lasting and profitable relationships with customers. In this context, the aim of this paper is to predict firms' performances in online customer complaint management using machine learning algorithms. This study utilizes data obtained from Turkey's largest and well-known third-party online complaint platform and employs three popular machine learning classifiers including decision tree (DT), random forests (RF) and support vector machines (SVM). The results show that the RF algorithm performed better in firms' performance prediction compared to other ML algorithms.