I-Corps Teams: STEM Skills Genome

这个I-Corps项目的更广泛的影响/商业潜力是通过更好地将技能和先天兴趣与学位课程，特别是新颖的STEM课程相结合，来提高学生并最终提高员工的参与度。为了应对对新型工作日益增长的需求，计算基因组学和音乐技术等学位课程将历史上不同的领域结合起来。 该项目使学生能够发现与他们相关的传统和新兴专业。通过提供可操作的见解和更好的利益调整，这减少了大学期间改变专业的摩擦（目前约80%），并开始缓解工作场所普遍缺乏参与（约70%）。 与传统的将GPA、考试成绩、非结构化论文和简历与学校、专业和职位空缺相匹配的方法相比，该项目可能会彻底改变学生识别、培训和为未来职业做准备的方式。这个I-Corps项目基于一种名为Skills Genome的统一多维数据表示方法的新技术，该技术正在申请专利。Skills Genome可以被几个机器学习模型利用，允许捕获和建模复杂的学生数据输入，如批判性思维，沟通，兴趣，领导力等。 通过使图的结构可用于多个机器学习模型，该方法提高了准确性、相关性并有助于扩展。 具体来说，这是在追踪学生吗的发展时间轴，这样他们就可以最好地确定他们所选择的职业所需技能的时间和顺序。 此外，通过大规模匹配个人资料，对潜在职业的新见解可以浮出水面，沿着实现这些目标所需的后续步骤。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is to increase student and eventually, employee engagement, by better aligning skills and innate interests with degree programs, particularly novel STEM programs. In response to increasing demand for new types of jobs, degree programs such as Computational Genomics and Music Technology have combined fields that have historically been distinct. This project enables students to discover both traditional and emerging majors relevant to them. By providing actionable insights and better alignment of interests early on, this decreases the friction of changing majors (~80% currently) during college and begins to mitigate widespread lack of engagement (~70%) in the workplace. Compared with traditional methods that match GPAs, test scores, unstructured essays, and resumes, with schools, majors, and job openings, this project could revolutionize the way students identify, train and prepare for their future careers.This I-Corps project is based on a novel patent-pending technology of a unified multi-dimensional data representation method called Skills Genome. Skills Genome can be exploited by several machine learning models, allowing for capturing and modeling complex student data inputs such as critical thinking, communication, interests, leadership, etc. with temporal graphs. By making the structure of the graph accessible to several machine learning models, the method improves accuracy, relevance and facilitates scale. Specifically, this tracks the student?s development timeline, so they can best determine the timing and sequencing of skills needed for their chosen careers. Further, by matching profiles at scale, new insights into potential careers can be surfaced, along with the next steps needed to achieve them.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.