Deep learning and collaborative filtering for project based team recommendation

时间管理和时间表软件已经在各个行业中存在了几十年。如今，许多行业**都采用了自动时间跟踪系统。很明显，考勤表对任何**业务都很重要。然而，重要的挑战性问题仍然存在。其中包括：迟到和遗漏的时间表，难以辨认和不准确的时间表，以及人工输入错误。此外，时间表更多的是衡量投入，而不是提高产出的质量。为了应对这些挑战并释放创造性人才的全部潜力以获得更高质量的产出，我们希望开发一种创新的方法来使用时间表数据，以便使用人工智能（AI）更好地构建团队和项目协作。我们的行业合作伙伴**Dovico已开发时间管理软件25年；多年来，他们见证了考勤表的演变，如今，他们看到了基于机器学习技术开发更智能系统的巨大机遇。**该项目的目标是建立一个机器学习算法，该算法可以从可用数据中学习如何根据团队成员的工作行为和团队成员的互动来分配团队成员到项目中。

Time management and timesheets software has been around in various industries for decades. Many industries**have adopted automated time tracking systems today. It is obvious that timesheets are important to any**business. However, important challenging problems remain. Among them: late and missing timesheets,**illegible and inaccurate timesheets, and manual entry errors. Additionally, timesheets are more about measuring**inputs than with improving the quality of output. To tackle these challenges and unleash the full potential of**creative talents for higher quality output, we want to develop an innovative way toward the use of timesheets**data for better teams building and project collaboration using Artificial Intelligence (AI). Our industrial partner**Dovico has been developing time management software for 25 years; they have seen the evolution of**timesheets over the years and see today a huge opportunity to develop a more intelligent system based on the**use of machine learning techniques.**The objective of this project is to build a machine-learning algorithm that can learn from available data on how**to assign team members to projects based on their work behavior and team members' interaction.