Nikseresht, AliShokouhyar, SajjadTirkolaee, Erfan BabaeeNikookar, EthanShokoohyar, Sina2024-05-192024-05-1920240040-16251873-5509https://doi.org10.1016/j.techfore.2024.123268https://hdl.handle.net/20.500.12713/5681This work develops a novel approach based on Machine Learning (ML)-assisted Quality Function Deployment (QFD) to sift the gold from the stone. It includes Time-Varying Filter-based Empirical Mode Decomposition (TVFEMD), Deep Ensemble Random Vector Functional Link (DE-RVFL), and a Bayesian optimization algorithm for optimizing the shaped DE-RVFLTVF-EMD hyperparameters. This approach makes it possible for the proposed methods to be dynamic enough to deal with the data's volatility, complexity, uncertainty, and ambiguity. It is demonstrated that incorporating TVF-EMD to provide time-frequency analysis along DE-RVFL, and goal-oriented social media analytics boosts the performance of out-of-sample predictions statistically and compensates for the warranty data maturation effect. The proposed algorithm's Root Mean Square Error (RMSE) decreases by 23.37%-88.76% relative to other benchmark cutting-edge models. This study contributes significantly to the services management community. Using the proposed methodology, managers could create plans for warranty claims strategies that reduce inventory levels and waste while optimizing customer satisfaction, advocacy, and revenues. These merits provide incentives and support for policymakers to adopt advanced technologies, such as the ones developed and implemented in the current study, in warranty claims forecasting to improve accuracy and efficiency.eninfo:eu-repo/semantics/closedAccessWarranty Claims PredictionSocial Media AnalyticsQuality Function DeploymentTime-Frequency AnalysisDeep LearningDeep Ensemble Random Vector Functional LinkArticle201WOS:0011885399000012-s2.0-85185197179N/A10.1016/j.techfore.2024.123268Q1