Purpose The purpose of this study is to establish a comprehensive service recovery mechanism by analyzing different behaviors of customers with different personality traits after service failures and by proposing different service recovery measures that service providers could adopt based on diverse customer personality traits. Design/methodology/approach This paper constructs a service recovery mechanism based on a signaling game theory by considering customers and service providers as two players in the game and analyzing possible outcomes under both separating and pooling equilibria to achieve an optimized strategy and set of actions that allow the highest payoffs for both service providers and customers. Findings This study successfully simulated the separating equilibrium and pooling equilibrium between service providers and customers in a signaling game with incomplete information. It also provides a reference for service providers to design service recovery strategies after service failures. By using this model, when facing problems related to service failures and service recovery, service providers will have a better chance of increasing the service recovery success rate, improving customer satisfaction and achieving optimal payoffs for both themselves and their customers. Originality/value Based on concepts of service science, this study designed a service recovery mechanism by applying the signaling game from game theory and introducing personality traits theory to the service recovery scenario so that service providers are able to execute service recovery after service failures more effectively. This study proposed a service recovery mechanism based on the perspectives of both service providers and customers, considering the mutual influence of key variables related to both of them, as well as the context of service failures, customers’ personality traits and service providers’ available resources. Many studies have applied personality traits to different fields; however, to the best of authors’ knowledge, few studies have applied this concept to service-related subjects, and only the influence of employees’ personality traits on service providers has been discussed.

This paper first applies genetic algorithms to optimally design reinforced concrete isolated footings subjected to concentric loading. Based on the ACI Building Code, constraints are built by considering widebeam and punching shears, bending moment, allowable soil pressure, the development length for deformed bars and clear distance between deformed bars. Design variables consist of the width, length and thickness of the footing and the number of bars in the long and short directions, all of which are discrete. The objective function is to minimize the cost of steel and concrete in the footing. There are totally 144 cases of reinforced concrete isolated footings considered. The optimal results are randomly divided into three groups for the use of neural networks: training data, validation data and testing data. Two kinds of artificial neural networks are employed in this paper: two-layer feedforward backpropagation networks and radial basis networks. Linear regression analysis between the network outputs and targets of the testing data is performed to judge the accuracy of the neural networks. Numerical results show that the feedforward backpropagation network is very effective and has high accuracy with the correlation coefficients and the slope of the regression line being close to one and the y-intercept close to zero. Besides, it is better than the radial basis networks and needs much fewer neurons in the hidden layer.