Faculty, staff or current student? Take the UW Climate Survey

iSchool Capstone

2021

Project Logo

Rosetta Stone 2.0: Expanding the Language Metadata Table

The Language Metadata Table (LMT) is a standard set of language codes used in the media and entertainment industries. The LMT Working Group received several sets of requests for new language code additions and updates. I compared these requests to the existing coverage, performed background research to prepare the languages for ingesting, and made recommendations for inclusion. As a result, 95 languages have been sent to the LMT Working Group for review and inclusion, for an increase in coverage of almost 40%, while an additional 83 were sent to subcommittees and partner organizations for further review and discussion.
Project Logo

Security Review Process for Microsoft’s Mixed Reality team

Microsoft’s Mixed Reality team needs to integrate a document management system (DMS) into their organization for managing policy documents. Due to the sensitive nature of the team, the DMS must meet functional needs and baseline security requirements. Team Infognito developed a security review process and evaluated the security posture of multiple platforms. We recommended ServiceNow GRC based on our evaluation. The process provides the necessary tools for Mixed Reality to evaluate any third-party platform without having to create a new process each time. It is a scalable process which standardizes the procedures for application approval and saves the organization’s resources.
Project Logo

Smartsheet Identity and Access Management Automation

The current quarterly access review process at Smartsheet comes with a myriad of challenges. Smartsheet’s access reviews are time-consuming and draw upon a lot of resources. There’s a large company-wide communication effort to track changes in employee structure. Our Identity and Access Management Dashboard presents the Smartsheet Compliance team with employee change metrics tracked with custom automation, a report containing highlighted daily employee changes, and visualizations used to present a historical timeline of changes in employee structure. With our dashboard, Smartsheet’s Compliance team will be able to save time and resources and have key actionable insights to employee changes.
Project Logo

Sourcing additional information on private equity transactions

The world of private equity (PE), already formidable in size, is expected to see continued rapid growth in the coming years. Global PE assets under management are forecast to reach US$5.8 trillion by 2025. PitchBook tasked us with identifying additional sources of private-market info to supplement their robust information-architecture. Specifically, PitchBook requested publicly available, granular information pertaining to the investments made by an individual fund of an investor, known as deal-to-fund tagging.
Project Logo

WorkConnects: Your work community is just one connect away

Employees at mid- to large-sized companies are faced with many challenges when it comes to connecting with peers and cultivating new working relationships. It can be intimidating to make new friendships outside of your team, and demanding work schedules can make this even more difficult. WorkConnects aims to foster new workplace friendships by automatically matching employees based on their availability and interests.

2020

Project Logo

Assisting Seattle Small Business Owners during the COVID-19 Pandemic

The City of Seattle Office of Economic Development (OED) works with local businesses to promote innovation, equity, and economic mobility. The COVID-19 pandemic has highlighted existing disparities between business ownership, and the greater need to distribute resources to People of Color (POC)/non-white business owners. Restaurants represent the culture of a society, and support a range of industries. They have also been one of the hardest industries impacted during the pandemic. To assist the City during this challenging time, we produced a data dashboard to analyze survey data collected, and mitigation recommendations for POC/non-white restaurant owners impacted by the COVID-19 pandemic.
Project Logo

Azure Machine Learning: Understanding Behaviors That Lead to Customer Retention

The Microsoft Azure End to End platform team is invested in identifying an efficient way to steer revenue growth prospects and to further improve user experience as well as increase the customer retention rate. Our project involved the data validation, data quality check, metric definitions and automated pipeline building. Our analysis serves as a foundation towards data-driven decision making for customer retention. The result can be utilized to monitor the user behavior and performance in real time to provide the better service and garner customer loyalty.
Project Logo

C-Bike: Bike Locker Management

Cascade Bicycle Club handles 220 of King County Metro’s leased bike locker units and manages over 160 customers who rent these eco-friendly and affordable lockers. Cascade relied heavily on manual transactional processes to facilitate their bike locker leasing program. Our project, C-Bike, has successfully eased the process for this non-profit by creating a secure, data-integrable customer management database for locker administrators, and a clear, concise frontend locker rental webpage for customer inquiries. Through C-Bike, customers and administrators can have swift and more secure interactions, thus ensuring that these resources are quickly accessible to those who need them.
Project Logo

Husky Hub

Students are not able to afford food and vary their food choices through the current Housing and Food Services system. We wanted to mainly address the question: "How might Housing and Food Services in the University of Washington allocate finances, vendors, policy, and resources so that they can decrease the exploitation of student funds and improve student life by varying food choices through connecting with more partners?" Our Solution is Husky Hub, a web application focused on improving the student food service experience regardless of financial standing and building community through on campus resources and small business owners.
Project Logo

ML Enabled Predictive Quality

Talking Rain(TR) is a leading beverage company manufacturing sparkling water and other beverages. TR relies on manual quality assurance processes to identify non-optimal beverages before release into the market. Non-optimal products yield complaints from consumers and generate negative publicity for the company. The goal of the project was to leverage ML to identify hidden patterns and detect non-optimal lots to prevent their release into the market. Our ML model was able to identify 100% non-optimal lots at the cost of retesting few good lots. This data-driven approach has enabled TR to identify quality issues at co-packers early, ensuring proactive remediation.