The main objective of the research visit of the aCCoRdO project is the scientific collaboration between the seconded fellow (Dr. Ioanna Lykourentzou) and the team of the Carnegie Mellon University (in particular Prof. Steven Dow) on the topic of advanced computational techniques to optimize the use of humans in complex crowdsourcing environments. The other two objectives of the research visit are the expertise transfer between the fellow and the CMU researchers, and the investigation of further funding opportunities to sustain the collaboration between CMU and the institution of origin (CRPHT/LIST). The outcomes of this collaboration are threefold: i) producing internationally competitive new knowledge on the cutting-edge topic of crowdsourcing optimization accounting for human factors, ii) enabling the fellow to learn new skills that will allow her to progressively set up a competent team dedicated to complex crowdsourcing upon her return to Luxembourg and iii) building a longer-term collaboration between the two institutions. Crowdsourcing is acknowledged as one of the most promising new forms of computation, for the mass production of tasks and services, through the extensive use of human crowds. Nevertheless, the main assumption of current crowdsourcing approaches, for an endless, anonymous and fully replaceable crowd, brings along several disadvantages. These include the non-optimal utilization of the available crowd by placing a lot of unnecessary effort on the human element (e.g. assigning multiple workers per task to address quality concerns), the limiting of current applications to simple, low-complexity human tasks (in order to ensure that a large enough number of people can be found to handle the task), and the omission of the human factor (worker interests, motivations etc.) from current crowdsourcing optimization algorithms. Complex tasks, like product design or knowledge synthesis, which necessitate higher-level human skills (such as judgment ability, expertise, decision-making) suffer under the aforementioned “endless, anonymous, replaceable crowd” assumption. Since the number of people who can handle complex tasks is inevitably smaller (crowd of experts) these tasks necessitate a smarter worker selection process, the accounting for human factors to sustain motivation and the design of advanced, efficient algorithms that will optimize the use of humans and avoid “burning out” expert resources. Despite the above, current research approaches either focus mostly on low-complexity human tasks, or they do not account for human factors.