Participation recommendation system for crowdsourcing contests

• Statistical models of winner determination for crowdsourcing contests are proposed.
• The use of auxiliary information improves the accuracy of contest recommendation.
• Transfer learning is beneficial to address the sparsity of contest data.

We propose a novel participation recommendation approach for crowdsourcing contests including probabilistic modeling of contest participation and winner determination. Our method estimates the winning and participation probability of each worker and offers ranked lists of recommended contests. Since there is only one winner in most contests, standard recommendation techniques fail to estimate the accurate winning probability using only the extremely sparse winning information of completed contests. Our solution is to utilize contest participation information and features of workers and contests as auxiliary information. We use the concept of a transfer learning method for matrices and a feature-based matrix factorization method. Experiments conducted using real crowdsourcing contest datasets show that the use of auxiliary information is crucial for improving the performance of contest recommendation, and also reveal several important common skills.