Search

Design is increasingly adopted by organization as an innovation capability to renew and transform the firm and therefore acting as dynamic capability. However, few article address how firms build a new dynamic capability and especially in the case of the design capability. Based on a longitudinal case study of the building of design as an innovation capability within an insurance company, we suggest a capability-building framework: a capability is built by acquiring resources, deploying them in activities such as projects, capitalizing on the learning from one project to another, and thus building progressively knowledge that is then shared and diffused among the resources resulting in the renewal of their competences. This framework highlights a reinforcement dimension and distinguishes operations (Designing, spreading Design and managing Design) from building on these operations (building the Design expertise and transforming the organization through Design) in order to contribute to the firm’s resources renewal.

International audience; Responses of many real-world problems can only be evaluated perturbed by noise. In order to make an efficient optimization of these problems possible, intelligent optimization strategies successfully coping with noisy evaluations are required. In this article, a comprehensive review of existing kriging-based methods for the optimization of noisy functions is provided. In summary, ten methods for choosing the sequential samples are described using a unified formalism. They are compared on analytical benchmark problems, whereby the usual assumption of homoscedastic Gaussian noise made in the underlying models is meet. Different problem configurations (noise level, maximum number of observations, initial number of observations) and setups (covariance functions, budget, initial sample size) are considered. It is found that the choices of the initial sample size and the covariance function are not critical. The choice of the method, however, can result in significant differences in the performance. In particular, the three most intuitive criteria are found as poor alternatives. Although no criterion is found consistently more efficient than the others, two specialized methods appear more robust on average.