Predicting the relationship between consumer buying behavior (CBB) and consumption metaphor (CM) through machine learning (ML)

Abstract The use of machine learning (ML) in the field of marketing has recently gained momentum in parallel with the development of technology. ML not only enables customers to predict their digital actions but also supports targeting the right customers with the best content at the right time. The study aims to predict the relationship between consumer buying behavior (CBB) and consumption metaphor (CM) through ML. In this context, the application of the study was built on two scenarios. In the first scenario, CBB is associated with the CM to confirm the ML estimation. In the second scenario, it is aimed that ML both predicts CBB and estimates and confirms the effect of CM on CBB. As a result, the k-nearest neighbors algorithm was able to predict consumers at the rate of 91.02% accuracy and predict consumers who do not intend to have tattoos at the rate of 90.98%. When the CM is considered, ML predicted consumers at the rate of 78.33% accuracy, and predicted consumers who do not tend to buy at the rate of 79%.