Customer feedback as a learning source for AI marketing: utilizing NPS and reviews

the purpose of this study is to analyze the potential of using the Net Promoter Score (NPS) in the context of AI marketing, summarizing the prospects for automating data collection, processing customer reviews, and training intelligent systems to improve customer experience. Methods: the study employs methods of theoretical analysis, synthesis, comparison, generalization, bibliographic description, and formal-logical analysis of scientific literature. Findings: the paper presents the structure of NPS data, classifies sources of textual reviews, and proposes methods for automating their collection and processing. It substantiates the combined use of numerical and textual data in the formation of training datasets for AI. The effects of implementing such solutions are demonstrated: improved personalization, reduced churn, and the development of behavioral loyalty patterns. Conclusions: the results highlight the feasibility of integrating NPS and customer reviews into intelligent customer experience analysis systems. This integration creates opportunities for developing human-centered AI marketing strategies that emphasize empathy, proactivity, and predictive analytics.

NPS, customer loyalty, artificial intelligence, AI marketing, machine learning, review analysis, personalization, sentiment analysis, digital analytics