Advertising Statement Optimization System based on Consumer Type Classification

In marketing optimization, consumer behavior research continues to advance while practical theories remain underdeveloped. This study addresses this gap by proposing an advertising optimization system integrating Regulatory Focus Theory with the Consumer Style Inventory (CSI) to generate personalized advertisements. The system classifies consumers based on purchasing characteristics and creates tailored advertising statements optimized through machine learning. We conducted experiments in which participants interacted with the system in a virtual shopping environment. Results indicate that the proposed system successfully categorizes consumers according to their purchasing characteristics and generates effective advertisements that increase selection rates. Specifically, optimization reached approximately 75% effectiveness by the sixth interaction. Our findings suggest that personalized advertisement generation incorporating both regulatory focus and consumer style classification effectively promotes purchasing motivation. This research contributes to the practical application of theoretical consumer behavior models in real-world marketing scenarios.