Scholarlink

<p>This study attempts to develop and evaluate a predictive framework for evaluating the service quality perceptions of Indian shopping mall visitors by integrating traditional retail service quality assessments with Machine Learning algorithms. A quantitative research design is adopted, with primary data collected from 525 shopping mall visitors across major urban hubs via mall intercept surveys. A structured questionnaire is developed on the basis of the Retail Service Quality Scale items adapted to the Indian malls. Machine learning (ML) algorithms such as Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and Support Vector Machine are trained and evaluated using five-fold cross-validation. The findings suggest that the Random Forest model demonstrates the highest predictive accuracy and robustness. Furthermore, the Feature Importance analysis identifies Mall Client Care and Accessibility as the primary factors shaping shoppers’ perceptions. The resulting framework provides mall managers with a scalable, proactive tool to predict visitors’ perceptions, optimize service-delivery infrastructure, and thereby strengthen overall mall competitiveness.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Decoding the shopping mall experience: predictive modeling of service quality perception using machine learning algorithm

  • 期刊论文

  • 发表日期：

    2026年8月3日

查看全文
  • Riya Ghosh,
  • Dipa Mitra

摘要

This study attempts to develop and evaluate a predictive framework for evaluating the service quality perceptions of Indian shopping mall visitors by integrating traditional retail service quality assessments with Machine Learning algorithms. A quantitative research design is adopted, with primary data collected from 525 shopping mall visitors across major urban hubs via mall intercept surveys. A structured questionnaire is developed on the basis of the Retail Service Quality Scale items adapted to the Indian malls. Machine learning (ML) algorithms such as Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and Support Vector Machine are trained and evaluated using five-fold cross-validation. The findings suggest that the Random Forest model demonstrates the highest predictive accuracy and robustness. Furthermore, the Feature Importance analysis identifies Mall Client Care and Accessibility as the primary factors shaping shoppers’ perceptions. The resulting framework provides mall managers with a scalable, proactive tool to predict visitors’ perceptions, optimize service-delivery infrastructure, and thereby strengthen overall mall competitiveness.