Leveraging Azure Automated Machine Learning and CatBoost Gradient Boosting Algorithm for Service Quality Prediction in Hospitality: Dataset from the Indian Hotel Industry

The present study endeavours to ascertain whether all the dimensions of SERVQUAL carry equal weight in terms of their impact on overall service quality. Questions were framed to measure each of the dimensions of SERVQUAL with different predictor variables: gender, age, marital status, highest level of education, and frequency of staying at the hotel. Machine learning models are used to find the importance of each feature against a dimension. Comparative modeling of feature importance was done using the CatBoost gradient boosting technique and Microsoft Azure Automated Machine Learning studio. The result confirmed an excellent similarity between CatBoost's drawn feature importance and those obtained from Azure auto ML studio. The results of the investigation enable decision-makers to determine which dimension is dependent on specific predictors, allowing them to focus on targeted improvements.

本研究旨在验证SERVQUAL的各个维度在影响整体服务质量方面是否具有同等的重要性。研究者构建了一系列问题，用以测量SERVQUAL的各个维度，并采用性别、年龄、婚姻状况、最高教育水平和入住酒店的频率等不同预测变量作为测量指标。通过机器学习模型，研究者发现了每个特征与各维度之间的重要性关系。采用CatBoost梯度提升技术和Microsoft Azure自动机器学习工作室进行了特征重要性的比较建模。结果表明，CatBoost提取的特征重要性与Azure自动ML工作室获得的结果之间具有卓越的相似性。该研究的成果使得决策者能够确定哪些维度依赖于特定的预测变量，从而有针对性地进行改进。