Перейти к основному содержанию
AkademIndex

Продукты

Для разработчиков

AkademBaseскороОткрытый API экосистемы
Латиница
Статья

Personalized marketing: Leveraging AI for culturally aware segmentation and targeting

Franciskus Antonius AlijoyoCenter for Risk Management and Sustainability, School of Business and Information Technology STMIK LIKMI, Bandung, IndonesiaTaheseen Shaikh Abdul AzizDepartment of Marketing and Business Analytics, Faculty of College of Business and Tourism, University of Prince Mugrin, Madina, Saudi ArabiaNadir OmerDepartment of Information Systems, College of Computing and Information Technology, University of Bisha, Bisha 61922, Saudi ArabiaNadia YusufDepartment of Economics, Faculty of Economics and Administration, King Abdulaziz University, Jeddah, Saudi ArabiaM. Dhiliphan KumarDepartment of Management Studies, Velammal College of Engineering and Technology (Autonomous), Madurai, Tamil Nadu, IndiaA. RameshDepartment of CSE, Graphic Era Deemed To Be University, Dehradun, Uttarakhand 248002, IndiaZoirov UlmasInformation Systems and Technologies Department at the Tashkent State University of Economics, UzbekistanYousef A. Baker El–EbiaryFaculty of Informatics and Computing, UniSZA University, Malaysia
ABI

Аннотация

In today’s competitive global market, personalized marketing is crucial for businesses aiming to engage diverse audiences effectively. This study examines the potential of AI-driven methodologies, specifically K-means clustering and Local Interpretable Model-Agnostic Explanations (LIME), in designing impactful marketing strategies. Using the Mall Customer Dataset, which includes consumer attributes like gender, age, annual income, and spending scores, this research develops a segmentation framework enriched with additional features, such as purchasing behavior during specific events, individual preferences, and demographic norms. K-means clustering is employed to group customers into meaningful segments based on shared behavioral patterns, with the Elbow Method and Silhouette Score ensuring optimal cluster determination. To enhance the interpretability of clustering results, LIME is used to explain the influence of demographic and behavioral factors on cluster formation. This explainability enables marketing teams to understand the rationale behind customer segmentation, promoting transparency and ethical AI usage. By integrating AI-driven segmentation with explainable AI, the framework offers deeper customer insights while aligning strategies with diverse consumer values. The approach empowers businesses to craft ethical and personalized marketing campaigns tailored to unique consumer needs. This study not only supports more effective engagement strategies but also emphasizes the importance of transparency in AI-driven marketing, fostering trust and alignment with consumer expectations. Actionable recommendations are provided for businesses aiming to enhance market presence and create impactful, tailored campaigns that resonate with their audience. The proposed K-Means-LIME framework achieved superior performance with an MSE of 0.9212 and an MAE of 0.9874, demonstrating its effectiveness in delivering precise and interpretable customer segmentation insights.

Темы

Идентификаторы

Цитирования и источники

Показатели — AkademScholar · Скоро