Olivares-Rodríguez, C.Guenaga, M.Garaizar, P.2017-12-132017-12-132017-07Dyna (Spain). Volume 92, Issue 4, July 2017, Pages 449-4550012-7361http://dx.doi.org/10.6036/8243http://repositorio.unab.cl/xmlui/handle/ria/4879Indexación: Web of Science; Scopus.Research, development and innovation are the pillars on which companies rely to offer new products and services capable of attracting consumer demand. This is why creative problem-solving emerges as one of the most relevant skills of the 21st century. Fortunately, there are many creativity training programs that have proven effective. However, many of these programs and methods base on a previous measurement of creativity and require experienced reviewers, they consume time for being manual, and they are far from everyday activities. In this study, we propose a model to estimate the creative quality of users' solutions dealing with heuristic problems, based on the automatic analysis of query patterns issued during the information search to solve the problem. This model has been able to predict the creative quality of solutions produced by 226 users, reaching a sensitivity of 78.43%. Likewise, the level of agreement among reviewers in relation to the creative characteristics is evaluated through two rubrics, and thereby, observing the difficulties of the manual evaluation: subjectivity and effort. The proposed model could be used to foster prompt detection of non-creative solutions and it could be implemented in diverse industrial processes that can range from the recruitment of talent to the evaluation of performance in R&D&I processes.enComplex problem solvingInformation searchInnovationMachine learningQuery patternArtículo