Abstract
In the current study, the author implemented cohort analysis methodology of machine learning (ML) to assess the rate of consumers' complaint retention behavior toward firms. The author obtained a three-year range of data on customer complaints from the Consumer Financial Protection Bureau's website. After removing the missing data from the customer complaints dataset, the current study also uses the cohort analysis approach of ML to assess the rate of consumer complaints retained by businesses. According to the findings, organizations retain a significant portion of complaints. This study adds to the body of knowledge on consumer complaining behavior (CCB), especially by creating and deploying unsupervised machine learning-based technique to conceptualize consumers' complaint behavior in the financial service providers industry. Moreover, professionals will benefit greatly from this research.
TopIntroduction
Similar to the manufacturing industrial revolution and the rise of the eighteenth century, the service area appears to be at a crossroads in terms of productivity increases and service industrialization. Virtually all service industries will be transformed by promptly developing technology that grows cheaper, faster, smarter, and better (Hossain and Rahman, 2021a; Hossain et al., 2021; Wirtz et al., 2018; Wirtz and Zeithaml, 2018), such as the use of artificial intelligence (AI). Basically, AI is altering digital marketing techniques at a breakneck pace (Mogaji et al., 2020). In the financial services sector, AI is defined as a system aided by technology that evaluates real-time provision circumstances using data collected from physical and/or digital sources to deliver tailored recommendations, solutions, and alternatives to purchasers' problems or inquiries, even intricate ones (Xu et al., 2020). Machine learning (ML) is a subset of AI that involves the automatic recognition of significant patterns in large datasets (Hossain and Rahman, 2022b; Pashchenko et al., 2022). The goal of ML technologies is to make algorithms more efficient by assuring their capacity to learn and adapt based on massive data analytics. Many industries, including financials, will continue to be impacted by machine learning and omnipresent data (Hossain and Rahman, 2022a). When vast amounts of data are entered into the system, machine learning tends to be more accurate in gaining insights and producing predictions (Hossain et al., 2022). The financial services business deals with massive amounts of data from everyday transactions, invoices, payments, vendors, and consumers, all of which are ideal for machine learning. Also, it will be more advantageous for businesses to understand their customers' feelings continuously.
Key Terms in this Chapter
Consumer Complaint Behavior (CCB): A collection of consumer dissatisfaction responses is known as complaint behavior. It is an outward display of unhappiness, but it is only one factor that influences this behavior. Complaint behavior may be broken down into several sorts of responses, as well as a process.
Machine Learning: is a sort of data analysis that uses artificial intelligence to automate the process of developing analytical models. It's a branch of AI based on the premise that robots can learn from data, discover patterns, and make judgments with little or no human involvement.
Cohort Analysis: is a common method for businesses to acquire a deeper understanding of their consumers' behavior. It provides priceless insight into consumer behavior, which we can use to develop successful growth plans and enhance decision-making
Consumer Complaint: A consumer complaint, also known as a customer complaint, is a statement of discontent directed towards a responsible party on behalf of a customer. A customer complaint is any written, electronic, or oral message alleging deficiencies in the identity, quality, longevity, dependability, safety, or performance of a product or service that has been placed on the market.