PurposeConventional approaches such as Data Envelopment Analysis (DEA) and Fuzzy Data Envelopment Analysis (FDEA) cannot effectively account for uncertainty, which can lead to imprecise decision-making. Furthermore, these methods frequently rely on precise numbers, ignoring the inherent uncertainty of real-world data. To address this gap, the research question arises: How can we develop a methodology that combines Z-number theory and FDEA to provide a comprehensive assessment of residency preferences in European countries while accounting for uncertainty in information reliability? The proposed methodology aims to fill this gap by incorporating Z-number theory and FDEA.Design/methodology/approachThe proposed study assesses residency preferences across 39 European countries, focusing on key factors like environment, sustainability, technology, education, and development, which significantly influence individuals' residency choices. Unlike conventional DEA and FDEA approaches, the proposed method introduces a novel consideration: dependability. This inclusion aims to refine decision-making precision by accounting for uncertainties related to data reliability. The proposed methodology utilizes an interval approach, specifically employing the a-cut approach with interval values in the second step. Unlike using crisp values, this interval programming resolves formulations to determine the efficiencies of decision-making units (DMUs).FindingsThe comprehensive findings provide valuable insights into the distinctive factors of European nations, aiding informed decision-making for residency choices. Malta (75.6%-76.1%-75.8%), Austria (78.2%-78%-76.1%), and the United Kingdom (79.3%-78.4%-77%) stand out with distinct characteristics at levels of a = 0-a = 0.5-a = 1, assuming the independence of variables of the overall evaluation. Individual consideration of each factor reveals various countries as prominent contenders, except for the environmental factor, which remains consistent across countries.Originality/valueTraditional DEA models encounter challenges when dealing with uncertainties and inaccuracies, particularly in the evaluation of large systems. To overcome these limitations, we propose integrating Z-numbers—a powerful mathematical tool for modeling uncertainty—into the conventional DEA process. Our methodology not only assesses the effectiveness of countries across various socio-economic and environmental metrics but also explicitly addresses the inherent uncertainties associated with the data. By doing so, it aims to enhance the precision of decision-making and provide valuable insights for policymakers and stakeholders.