You are here

Home » Meetings » Invited Paper Session Abstracts - The Mathematics of Data Science

Invited Paper Session Abstracts - The Mathematics of Data Science

MAA Invited Paper Session

The Mathematics of Data Science

Please note: all sessions are listed in Eastern Daylight Time (EDT = UTC-4:00)

Saturday, August 5, 3:30 p.m. - 5:50 p.m., Ballroom A

The fundamentals of data science are drawn from mathematics, statistics, and computer science. However, there is a lack of clarity on what it actually means to be a data scientist and how to prepare students in data science. Given that real-world data lies in a context domain, the work of data science requires interdisciplinary domain expertise that may include the humanities, social sciences, and health sciences. To carry out the data lifecycle, the context domain must be considered throughout the data acquisition, analysis, and interpretation of findings. Even though many mathematical faculty have either taken or taught the ‘foundational courses’ in the fundamentals of data science, others may still be resistant to incorporating data science into their academic programs due to the myriad of challenges.

This session will feature mathematicians who will share how they are advancing data science teaching and research, along with their tools and applications. From developing academic programs to engaging students in culturally relevant data science, health informatics, sports analytics, etc., the session will demonstrate how mathematics catalyzes innovations. The presenters will showcase work being done across a range of academic institutions with industry partners from the mathematical perspective. We envision talks on probabilistic tools in data analytics for sports, complex systems and adaptive networks in data science, culturally responsive and justice-oriented approaches to teaching data science, and statistical tools in data analysis for quantitative social justice, among others. This session will also highlight the data science focus and anticipated findings of the February 2024 Special Issue of the American Mathematical Monthly, with Anna Haensch and Talitha Washington serving as Guest Editors.

Organizers:
Talitha Washington, Clark Atlanta University
Anna Haensch, Tufts University
Della Dumbaugh, University of Richmond

A Bayesian Hierarchical Model for On-Demand Digital Media

3:30 p.m. - 3:50 p.m.
Kobi Abayomi, Seton Hall U and Gumbel Demand Acceleration

We model “On-Demand” - or asynchronous impressions - of digital media inventory as two-stage, phase shift process. We discuss idiomatic features of a Bayesian Hierarchical Model for this process

Mathematical Models in the Sociological Imagination

4:00 p.m. - 4:20 p.m.
Nathan Alexander, Morehouse College

This talk presents an abstract study of mathematical and statistical modeling using methods from mathematical sociology that are rooted in the ideas of the sociological imagination. The sociological imagination allows us to examine how social systems interact and influence one another and we consider interpretations of these social systems using an integrated and critical approach to mathematical modeling. More specifically, we explore integrated modeling approaches focused on neighborhood composition and land ownership in the U.S. context.

Community-driven Data Science for Social Justice Research Practices

4:30 p.m. - 4:50 p.m.
Carrie Diaz Eaton, Bates College

Community-research partnerships have been to drive impactful scholarship across many fields such as healthcare and education. These collaborative relationships should also drive impactful and insightful work in data science for social justice research. We discuss some principles behind developing such collaborations, using as an example of supporting local community advocacy in Providence, Rhode Island with partners Nuevas Voces and the Woonasquatucket River Watershed Council.

Non- family Reason Internal Migration and Their Socio-economic Characteristics

5:00 p.m. - 5:20 p.m.
Binod Manandhar, Clark Atlanta University

Among the internal migrants a large proportion migrates due to family reasons, and they are less attracted by the gap in available opportunities between the place of origin and destination. This study analyzes internal migration data from the national living standards household survey 2010/11 data from Nepal. There are a small proportion of the migrants who migrated because of non-family reasons like higher salary, opportunities, easier urban lifestyle, higher education, but they have different characteristics than other populations. This study shows that though the non-family reason internal migration populations are small, they occupy a good proportion in the top rich quintile group of the nation and shows that they have better socio-economic status than other populations.

The Role of Mathematics in Undergraduate Data Science Programs

5:30 p.m. - 5:50 p.m.
Talitha Washington, Clark Atlanta University and Atlanta University Center

While data science is in high demand both in research and in the workplace, what is needed to prepare students for a data-driven workforce remains unclear. Even though mathematics is essential in data science, the role of how mathematics contributes to undergraduate data science programs remains unclear. This presentation will provide insights into how mathematics contributes to undergraduate data science education and how to build and leverage transdisciplinary and industry partners to enhance the undergraduate experience.

 

Year: 
2023