Causal Learning–Based Data Envelopment Analysis for Explaining Inefficiency in Beauty Clinics Providing Dermatological and Laser Services

This study aimed to evaluate the efficiency of active beauty clinics providing dermatological and laser services in Mashhad. For this purpose, the input and output data of ۴۰ clinics were simulated and assessed using a combination of Data Envelopment Analysis (DEA) and causal learning to not only measure efficiency but also identify the main sources of inefficiency. The results indicated that only a limited number of clinics achieved full efficiency, while the majority faced varying degrees of inefficiency. Causal analysis revealed that the lack of advanced equipment, insufficient working hours of staff, and internal process misalignments were the most significant contributors to inefficiency. Scenario simulations showed that upgrading equipment and optimizing staff working hours could significantly improve the average efficiency of the clinics, and a combined implementation of improvement measures had the greatest positive impact on clinic performance. These results highlight the importance of resource planning, productivity management, and evidence-based decision-making in enhancing service quality in clinics and provide practical guidance for managers and policymakers.

کلیدواژه ها:

Data Envelopment Analysis (DEA) ، Dermatological and Laser Services ، Efficiency ، Inefficiency ، Causal Learning