Abstract:

Data science and analytics is an emerging transdisciplinary area comprising computing, statistics, and various application domains including medicine, nursing, industry and business applications among others. A significant shortcoming of the current graduate curriculum in the U.S. is that scientists and engineers are well trained in their own areas of specialty but lack the integrative knowledge needed for new scientific discoveries and industry applications made possible by data science and analytics. To address these shortcomings, we proposed to NSF a new model of convergence education through experimental learning consisting of testbeds, boot-camps, and case studies. Our main goal is to create a novel graduate curriculum with intensive convergence activities, which also include transdisciplinary research projects.
In 2020 we received $2.4 million funding from NSF to establish and launch such a graduate program and train future data scientists from various disciplines. In this paper we report results based on two cohorts of graduate students who successfully completed the program and received Master degrees in data science and analytics. Our main training elements of our transdisciplinary curriculum included the development of normalization courses and the creation of different testbeds for various application domains. Normalization courses were used to address various background of students entering the program. Our transdisciplinary and convergent research themes were focused on three data science and analytics areas: (i) medical and healthcare applications, (ii) industry applications, and (iii) data science technologies. To address these, we created a transdisciplinary curriculum for graduate students in data science and analytics, where each course was developed by at least two faculty members from two different disciplines. In order to integrate research and training, we used Data Science and AI Laboratory to develop multiple testbeds for different application domains. Each testbed included computer platform, software tools, and set of learning modules. We provided a detailed evaluation and assessment plans including a logic model in order to anticipate outcomes and perform formative evaluation. A total of 20 trainees funded by NSF completed the program in the last 2 years, received the graduate degrees, and published research papers and patents based on research conducted as the part of the program.
We expect that the proposed program will drive graduate education in data science and analytics nationwide. The proposed plan included the development of an innovative training program for Master and PhD students from various departments, which consists of normalization courses, in-depth elective courses, transdisciplinary research activities, professional development workshops, and hands-on, testbed-driven education.

Keywords:

Data science, data analytics, transdisciplinary curriculum, normalization courses.