EAGER: BIGDATA: SMART Data - Academic Success Made Affordable, Rapid, and Timely through Integrated Data Analytics

数据科学技术已经彻底改变了许多学术领域，并在商业领域带来了巨大的收益。迄今为止，在解决美国教育体系中的关键问题方面，特别是在理解科学、技术、工程和数学（STEM）的学习和学习环境、扩大STEM的参与以及提高传统上未得到STEM教育的学生的保留率方面，它们没有得到充分的利用。教育和人力资源理事会通过推进大数据科学与工程基础与应用的关键技术和技术（BIGDATA）项目的目标是推进旨在理解和解决这些关键问题的基础研究，并促进数据科学在教育研究中的应用。这个探索性研究的早期概念资助（EAGER）将寻求了解数据处理和分析系统的背景和主干，这些系统可以使用学院和大学已经拥有的标准类型的数据(例如，来自他们的学习管理系统、行政数据系统、以及咨询系统)为学生和教师提供预测和建议，以提高学生在大学取得成功并按时毕业的比例。这对于提高两年制和四年制大学的毕业率具有巨大的潜力，这可以降低家庭和学生的大学成本。此外，它还具有极大的潜力，可以增加STEM领域中代表性不足的少数族裔的吸引力和保留率，因为它将确定所有学生成功按时毕业的障碍。团队的愿景是最终构建一个集成关键数据源的数据平台，并提供利用这些数据源的重要见解的工具。数据来源类型为：1)STEM专业本科生学业轨迹纵向数据；2)学习管理系统（LMS）的学生活动记录，3)来自各种来源的文本数据，如顾问。这些工具将包括：1)学生、教师和管理人员可以看到学生学习路径的GUI； 2)学生、教师和顾问之间交流的门户。该系统将帮助学生、教师和管理人员参与数据驱动决策（D3M），围绕学术途径成功并按时从大学毕业。探索性研究早期概念基金（EAGER）将解决为实现这一愿景而必须承担的许多挑战，并以各种方式为相关社区提供应对这些挑战的解决方案。对于这个早期概念项目，团队有四个目标。首先是检查现有的数据和预测模型，以了解学生的成功和保留，并建立一个应用程序和数据类型的目录，可用于围绕这些结果的决策。第二个目标是描述设计规范，包括构建数据平台所需的数据类型、算法和机器学习技术。第三是对大学生、教师和管理人员的D3M培训计划的关键要素进行试点研究。最终目标是开发一个设计框架，从头开始构建道德、隐私和安全。所有产品都将以出版物、课程或软件的形式在GitHub等公共论坛上公开共享。

Academic Success Made Affordable, Rapid, and Timely through Integrated Data AnalyticsData science techniques have revolutionized many academic fields and led to terrific gains in the commercial sector. They have to date been underutilized in solving critical problems in the US educational system, particularly in understanding Science, Technology, Engineering and Mathematics (STEM) learning and learning environments, broadening participation in STEM, and increasing retention for students traditionally underserved in STEM. The goals of the Directorate for Education and Human Resources through the Critical Techniques and Technologies for Advancing Foundations and Applications of Big Data Science & Engineering (BIGDATA) program are to advance fundamental research aimed at understanding and solving these critical problems, and to catalyze the use of data science in Education Research. This Early Concept Grant for Exploratory Research (EAGER) will seek to understand the background and backbone of systems of data processing and analytics that can provide insights using standard types of data that colleges and universities already have (for example, from their Learning Management Systems, administrative data systems, and advising systems) to provide predictions and recommendations to students and instructors to increase the percentage of students who succeed in college and graduate on time. This has terrific potential to increase graduation rates at two- and four-year institutions, which can lower college costs for families and students. In addition, it has terrific potential to increase the attraction and retention of underrepresented minorities in STEM fields, as it will identify barriers for all students to graduating successfully and on time.The team vision is to eventually build a data platform that integrates key data sources and provides tools that leverage important insights from these sources. The types of data sources are: 1) longitudinal data from undergraduate students on their academic trajectories in STEM majors; 2) Learning management system (LMS) records of student activity, and 3) text data from a variety of sources, such as advisors. The tools will include a 1) GUI for students, teachers and administrators to see student academic pathways and 2) a portal for communication between students, faculty and advisors. This system will help students, teachers and admistrators engage in Data Driven Decision Making (D3M) around academic pathways to successful and on time graduation from college. This Early Concept Grant for Exploratory Research (EAGER) will solve many challenges that must be undertaken to achieve this vision and provide the solutions to those challenges to relevant communities in a variety of ways. The team has four goals for this early concept project. The first is to examine existing data and predictive models for understanding student success and retention and build a catalog of applications and data types available for decision making around pathways to these outcomes. The second goal is to describe design specifications, including data types, algorithms, and machine learning techniques that are needed to build the data platform. The third is to pilot research on critical elements of a D3M training program for undergraduate students, instructors and administrators. The final goal is to develop a design framework that builds ethics, privacy and security in from the ground up. All products will be made available as publications, curricula, or software shared openly on common forums such as GitHub.