Data Analysis
Data gathering, manipulation, analysis, and visualization
Visit the official UMSI website for the most up-to-date information on client based courses
Information on the site you are currently visiting is no longer being updated as of Summer 2021
SI 485: Information Analytics Project
What is Information Analytics?
In SI 485: Information Analytics Project, advanced undergraduate students deliver data-oriented solutions through the development and analysis of data sets, building tools to extract useful information for clients through manipulation, analysis, and visualization.
Deliverables
What do clients receive for participating in this course?
A written report
Additional deliverable(s) determined collaboratively between the students and the client, which may include any of the following:
New data sets
Additions to existing data sets
Code repositories
System-level documentation to instruct clients on using scripts generated for the project
Other negotiated deliverables
Client Eligibility
Who can participate?
Potential clients should meet the following criteria:
Able to meet with students in the fall to define project requirements
Able to provide a secondary contact who is technical and who can answer questions about the datasets
Able to meet with students throughout the winter semester while the project is in process
Able to provide, at a few designated milestones, feedback and evaluation that forms part of the students' final course assessment
Projects
What are some examples of successful projects?
Check out this video , this video & this video for completed project deliverables.
What kinds of projects are appropriate for the course?
Potential projects should meet the following criteria:
Data-centric and revolve around large-scale datasets that require distributed computing and data manipulation, analysis, and visualization that cannot be performed on a personal computer.
Involve significant technical work, with corresponding amounts of programming and/or data analysis scripting
Require about 60 hours per week of work during the winter semester (about 15 hours per student per week)
Desirable projects may include the following:
Parsing, analyzing and interpreting Web log data for your organization/commercial enterprise
Using enterprise-scale data to improve performance, outcomes, or understanding of a problem
Developing a data manipulation/cleaning pipeline with Web-based visual summaries for your dataset(s)
Questions about data that require more than one component of data analysis or management to address
What kinds of projects are NOT appropriate for the course?
Less desirable projects may include the following:
Work on mission-critical components or processes with critical dependencies on other projects
Projects that do not involve significant technical or programming work
Projects without well-defined outcomes or paths to judging success
What are some examples of successful projects?
Accessing Justice—Connecting Low Income Clients with Affordable Attorneys. Students developed an algorithm to create visualizations for the pro bono division of the Chicago Bar Foundation. They were tasked with manipulating variables like poverty level, geographic location, and the type of law cases clients sought, to produce meaningful visualizations that can help the Justice Entrepreneurs Project allocate funds toward proper channels.
Fighting Fire with Data. Students worked with leadership from Fort Myers Fire Department to gather, analyze, and build upon key data sources to develop a tool that can identify, define, and prioritize at-risk buildings.
Library Program Standardization. Students worked with the Public Library Association to build a tool for decision makers involved with Project Outcome that makes sense of survey data, gathered over three years from public libraries in the United States and Canada, through predictive statistical analysis and sentiment analysis.
Customer Segmentation and Creditworthiness Prediction Models. Students worked with Umati Capital to address small- and medium-sized enterprises' lack of access to capital by developing a customer segmentation and credit scoring prediction model to calculate default rate and offer loans among these businesses.
Arts Engagement. By using over 5,000 responses from students across all schools at the University of Michigan on their level and history of engagement with the arts, students used modern data analytic techniques on qualitative and quantitative data to help arts administrators determine key predictors and motivators in college arts engagement.
What do students do during the project?
How many projects are selected for this course?
Winter 2021: 17 projects selected
Winter 2020: 21 projects selected
Winter 2019: 20 projects selected
* Due to variability in the number of enrolled students each year, these numbers are subject to change and can be used as a rough estimate.
Timeline
SI 485 occurs in the Winter semester (January–April), with a preparatory course in the Fall semester (September–December)
June – August
Client submits project idea
Client Engagement Team (CET) reviews project idea and requests full project proposal
CET works with client to scope and refine proposal
September
Faculty choose proposals to present to students
Students choose their project
October – December
Students engage with clients to define a project plan and timeline, gather and explore data, and finalize anticipated scope and deliverables
January
Students begin project
April
Students finish project and provide deliverable(s) to client
Participate
How do I become a client?
Potential clients should complete this brief form with their contact information and a short summary of their project idea. Our Client Engagement Team will review your submission and reach out to you within 3 business days with next steps.
What if I don't have a project right now, but I'm interested in future opportunities or want to learn more?
If you don't have a specific project in mind for the upcoming semester, but would like to stay informed about future opportunities to work with students through our client-based courses or other programs, complete this registration form to be added to our mailing list.
Former Clients
Who's participated in the past?
What do they have to say?
"This project was something we've been trying to get done for a long time, but kept being de-prioritized. UMSI students acted as an extension of our team and were the resources we needed to hit our internal goals. The product, tech, and design teams have a better sense than ever of what information and themes are coming in through App Store reviews. The impact was huge."
Becky Roth, Sr Manager of Product Marketing Expedia Group
"The students provided an invaluable perspective that improved our risk profile work on a broad level, and allowed us to think through the risks implied in the data in a more consistent manner. They were dedicated, highly motivated, and technically adept in multiple technologies needed to create a solution. They helped us look at the data set in a new way and improve our product overall."
Dennis Neil, University of Michigan Information Assurance
"Our team focuses on the experience our customers have with our digital support materials. The UMSI students' work allows us to determine what we implement next for our users and the impact it will have on them. They've essentially given us the necessary data to back our team's big initiatives and track our impact—a project where we didn't have the proper headcount to really dig into."
Emily Gottschalk, Qualtrics