DATA SHACK 2024

Harvard-Politecnico di Milano Joint Program on Data Science

INTRO

We offer a two-part research collaboration coupled with an innovative "hands-on" educational experience. This collaboration will involve students and faculty from the Harvard John A. Paulson School of Engineering and Applied Sciences' Data Science and Computational Science and Engineering Master's programs at Harvard, as well as participants from the Master's Courses in Computer Science and Engineering, Communication Design, and Fashion Design at Politecnico di Milano.

Eight students, four from Harvard and four from Politecnico di Milano, will join together to solve problems within the data science context. Under the supervision of Harvard and Politecnico di Milano faculty, this activity will give students the opportunity to work collaboratively with real-world applications.

Problems will cross the disciplines of data management, machine learning, data analysis, statistics and mathematics, data visualization and user experience design. Students will craft their solutions by developing the methodology, software, visualization, and high-performance elements, testing, completing the solution, and finally producing final papers that may be submitted for publication.

This joint venture will provide an exciting research opportunity for graduate students in data science to apply their work to the problems of society.

INTRO

PARTICIPATING INSTITUTIONS

FOCUS OF THE PROJECT

Generative AI for Fashion

Analysis and improvement of maternal mortality numbers in the US

PROJECT TIMELINE

APPLICATION AND BENEFITS

POLIMI CONTACTS

HARVARD CONTACTS

PARTICIPATING INSTITUTIONS

Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) -
Office of Master's and Professional Programs (OMPP)

At Harvard SEAS, the Office of Master's and Professional Programs (OMPP) administers and bolsters SEAS master’s programs along with a spectrum of non-degree courses. The current roster of terminal master’s programs includes:

Computational Science and Engineering (offering both S.M. and M.E. degrees)
Data Science (S.M), a collaboration with the Harvard Faculty of Arts and Sciences (FAS) Statistics Department
MS/MBA: Engineering Sciences, jointly with the Harvard Business School
MDE: Master in Design and Engineering, a collaborative degree with the Harvard Graduate School of Design.

The master's programs in Computational Science and Engineering, as well as Data Science (S.M), offer students a robust core curriculum that strikes a harmonious balance between computer science, applied mathematics, and statistics. This foundational training, when coupled with the opportunity to delve into elective subjects, readies students to address challenges across diverse fields of their choosing. The curriculum is further enriched with project-based courses, fostering hands-on experience and encouraging collaborative problem-solving.

Politecnico di Milano

The master school in Computer Science and Engineering and the master school in Communication Design of Politecnico di Milano share the mission of creating qualified professionals, capable of understanding, monitoring and mastering the pressing needs of a continuously evolving society. The two schools offer master programs that produce several hundreds of top-quality graduates yearly.

The two schools are increasingly engaged in promoting interdisciplinary educational experiences with mixed teams of students; the interaction between engineers and designers produces very powerful forms of innovation, thanks to the mix of information technology and sound computational and mathematical foundations from one side, and creativity, design thinking and effective interaction design from the other. Both schools are engaged in new programs and courses centered on data science, which includes data-driven management, analysis, and visualization, with a problem-solving approach to training.

FOCUS OF THE PROJECT

Two projects are defined for the 2024 edition:

Generative AI for Fashion

This project aims to codify the integration of AI image-generation tools within the creative development process in the fashion design field.

The project line will focus on the inheritance of the Gianfranco Ferré archive that, since 2021, has become the core of the “Gianfranco Ferré Research Center - Digital Innovation for Cultural and Creative Industries” established by Politecnico di Milano following the Ferré family’s donation of the former Foundation’s archives and headquarters.

Specifically, DataShack’s project assets will be based on the archival database that counts about 40,000 digital records witnessing the designer’s activity through digitized technical drawings and illustrations, patterns, runway show images and videos, press releases and ADV pictures, as well as texts, lessons, and notes written by Ferré himself. Managing digital records and archival metadata will serve as a catalyst for exploring human-AI co-creation during the creative development phase, bridging fashion cultural heritage with innovative design approaches.

The project will explore the use of generative tools, such as Midjourney and alike, to generate accurate images based on natural language prompts or visual inputs, thus enabling the exploitation of texts and images of the Research Center’s archive. The capacity of human-artificial creativity to co-design original interpretations of archival fashion design garments will be tested, reflecting on novel creative process dynamics within the fashion system. What will be the results of this human-AI co-design experiment? Will the machine be able to reinterpret Ferré’s style, sticking to his design principles? Will the designer manage to control the generative process of AI? How will the human-AI collaboration be structured to achieve the optimal original design?

Analysis and improvement of maternal mortality numbers in the US

The likelihood of maternal mortality for women in America has risen by 50% in comparison to their mothers' generation, showing a continuous rise in maternal mortality over several decades. According to recent CDC data, almost one-third of women in America who gave birth in a hospital reported experiencing one or more forms of mistreatment, with Black and Native individuals being disproportionately affected, regardless of income or educational level.

Harvard T.H. Chan School of Public Health and Brigham and Women's Hospital's Ariadne Labs initiated the Delivery Decisions Initiative (DDI), which developed TeamBirth, a care process improvement that has been evaluated in a documented clinical trial and applied by hundreds of clinicians caring for tens of thousands of families at hospitals across the United States. Over the past five years, it has grown rapidly as hospitals and healthcare organizations have seen the results of the successful implementation. By the end of 2023, TeamBirth will be available in more than 130 hospitals across the country, with the aim of becoming the standard of care in the United States.

TeamBirth is based on two main concepts: simplifying shared decision-making and encouraging effective communication and collaboration. The program is designed to address all four aspects of the quadruple aim: enhancing patient experience, improving population health, reducing per capita costs, and reducing provider burnout.

While the TeamBirth initiative has shown promise in improving maternal health outcomes, there is a need for ongoing evaluation and refinement. This project proposes to utilize advanced language models to analyze postpartum surveys completed by thousands of mothers. The aim is to derive actionable insights that can further enhance the TeamBirth program, particularly focusing on reducing maternal mortality rates and addressing mistreatment and disparities in maternal health.

The objectives of the project include:

To deploy language models in summarizing and analyzing postpartum surveys from mothers who have participated in the TeamBirth program.
To identify areas where TeamBirth can be refined to further reduce maternal mortality and mistreatment.
To develop targeted interventions based on the insights gleaned from the survey analysis.

PROJECT TIMELINE

The project will be scheduled along the following phases:

Jan 18 - Jan 26, 2024: faculty and students kick-off the project jointly in Harvard.
Feb to Jul 2024: Student teams interact to develop their project under the osmosis of the capstone course, jointly tutored by Polimi and Harvard faculty.
March 8 - 15, 2024: faculty and students set up an intensive joint work week at POLIMI. As a result of this work, students deliver a mid-term presentation. Harvard students are scheduled to travel to Milano during their spring break, from March 8 to 15.
May 2024: Final workshop and presentation of results take place in remote mode at Harvard and POLIMI.

APPLICATION AND BENEFITS

POLIMI

This program will select students currently attending the second year of the Master (Laurea Magistrale) of Politecnico di Milano, two from Information Engineering and one from Design. Applicants should have obtained at least 40 CFU during their first year of Master studies, with an average grade above 25/30. Applications must be sent by email by Tuesday, November 7, 2023 to: alice.gentile@polimi.it. The email must include as a subject: "DATASCIENCE application + Name of the applicant + Faculty of the applicant (Design or Comp.Sci.)".

The application must include as attachments: an up-to-date record of exams, the English proficiency certificate, a CV (including a description of experiences of programming and of group projects); and a motivation letter explaining the candidate’s interest in this educational opportunity. Design students must also attach a portfolio including experiences with data visualization and group projects; Proved experience with HTML, JS, and digital prototyping is not required but welcome.

Notice that all the application material must be either attached or linked in the email, in the form of PDF files (possibly compressed). No relevant information shall be added directly to the email text.

Students may be interviewed by the selection committee. Selected students must attend the two planned full immersion weeks. In addition to the full immersion periods, they are expected to work throughout the semester by using the format of the Capstone Course, by interacting with professors of Politecnico and Harvard. They are expected to deliver a public presentation of their results at the end of the program and to participate in the trip to NY in January 2024.

HARVARD

Harvard students must be in a Harvard master’s or PhD program. The Data-Shack program is being offered as a part of the Capstone course, so students signing up for this program must commit to taking this course during the spring semester.

Students are required to be on campus and participate in program activities with peers from Politecnico from January 18 to January 26 (Note that this includes some days prior to the official start of the spring semester).
Students must be available to travel to Milan during the week of spring break in March. Students must commit to collaborating with peers at Politecnico throughout the entire spring semester and will be expected to deliver a public presentation of their results at the end of the program.

The four students chosen to participate will be required to pay a $150 deposit to secure their spot in this program. OMPP will cover airfare, double occupancy hotel, and some meals. Students are required to pay for some meals and additional expenses.

A complete application includes submission of the form linked and emailing your resume as a PDF to Sheila Coveney, OMPP Director of Master's Programs at coveney@seas.harvard.edu, before December 1st.