Does country-of-origin brand personality generate retail customer lifetime value? A Big Data analytics approach

• DOI: 10.1016/j.techfore.2017.06.034
• Publication Date: 2017-07-29T10:46:53Z
• Authors: Lan-Lung (Luke) C...; Chin-Sheng Yang
• Keywords: 0502 economics and business; 05 social sciences

Abstract Many retail firms have witnessed the erosion of customer loyalty with the rise of e-commerce and its resulting benefits to consumers, including increased choices, lower prices, and ease of brand switching. Retailers have long collected data to learn about customer purchasing habits; however, many currently do not use data-mining analytics to increase marketing effectiveness by predicting future buying patterns and potential customer lifetime value, particularly to important segments such as loyal and potential repeat customers. Data mining can efficiently analyze large amounts of business data (“Big Data”) in an effort to forecast consumer needs and increase the lifetime value of customers (CLV). Previous studies on these topics primarily focus on conceptual assumptions and generally do not present empirically valid models. The present study sought to fill the research gap by using Big Data analytics to analyze approximately 44,000 point-of-sale transaction records for 26,000 customers of a Taiwanese retail store to understand how consumer personality traits relate to the country-of-origin (COO) traits (brand personality) of beer brands, and to predict potential customer lifetime value (CLV). The findings revealed that consumers tend to purchase and co-purchase brands with traits similar to their own personality traits (i.e., Japan—peacefulness, Belgium—openness, Ireland—excitement, etc.). Significantly, customers with the group of personality traits associated with “peacefulness” and “openness” were the most profitable customers among the five analyzed clusters (CLV value = 0.3149, 0.2635). The study provides valuable new insights into COO brand personality and consumer personality traits with co-purchase behaviors via data mining techniques, and highlights the value of extending CLV in developing useful marketing strategies.