Students on the JPMorgan Chase (JPMC) team will implement an AI chatbot assistant for payment client onboarding based on the Rasa platform to improve the onboarding efficiency, accuracy, and client experience within the business process of setting up client payment channels. All student team members will become JPMC 2025 Summer Interns, based in Chicago, IL.
Abstract:
JPMorgan Chase is the largest bank in the United States and offers Commercial & Investment Banking (CIB) and Markets & Securities Services across the country and globe. JPMC’s CIB division offers a broad suite of investment banking, market-making, prime brokerage, lending, and treasury and securities products and services to a global client base of corporations, investors, financial institutions, merchants, government, and municipal entities. Banking also includes payment services, which enables clients to manage payments globally across liquidity and account solutions, commerce solutions, clearing, trade and working capital. These payment clients’ flows are managed by multiple applications in payment technology, of which payment channels is a core segment.
COBRA (Client Onboarding Request App) is the strategic system for client setups in Payment channels. COBRA is integrated with multiple applications in the JPMC channels framework, and will integrate with even more systems in the future. In the roadmap, Cobra connects to 4 strategic systems for validation of input fields, and COBRA connects to 6 applications to setup the client flow. In 2023, COBRA supported more than 10,000 onboarding requests, and more than 8,000 support requests. Any inefficiencies, errors, or delays in the COBRA process results in a delay in client onboarding, and loss of revenue for the firm.
Using a New Chatbot interface, automated validations, and behind the scenes data analysis, the student team will develop a succinct onboarding experience which uses existing templates, defines patterns and prefilled forms for a faster, more accurate, and more intuitive onboarding process.
Impact:
This project will deliver a more efficient business operation that reduces time required, increases first entry accuracy, and increases visibility of the process. Current average elapsed time for payment client onboarding is 45 days, which we hope to reduce to fewer than 10 days using COBRA automation. We expect to reduce the effort spent on field validation, onboarding end to end tracking, and onboarding search from 2 headcounts to 0.5.
Scope:
Minimum Viable Product Deliverable (Minimum level of success)
- Literature review of all relevant techniques (Chatbot, NLU, Rasa tool), similar applications, patents, etc. and review current best practices within the sponsor’s organization
- Develop an understanding of the current business process, products/services offering, client interaction standards, and technical challenges, interview important stakeholders, articulate current failure modes, and develop most relevant use cases
- Demonstrate functional competence in the tech stack (Chatbots, Java, Python, NLU, NoSQL database, Spring Boot, Rest APIs, HTTPS based applications), by completing a “mini project”. Note – it is unlikely that any student would be fully competent in the entire tech stack before the project. Significant individual training effort is expected and required
- Utilize data analytics to characterize the previous use patterns
- Create a data analytics model of historical onboarding templates using a NoSQL database for data analysis to facilitate sharing with other JPMC groups
- Identify fastest onboarding patterns and recommend to applicable users as part of Chatbot experience
- Utilize data analytics to characterize the previous use patterns
- Complete first prototype of Rasa chatbot within the JPMC system
- May include suggesting answers pulled from other data systems, pre-formatting or reformatting the answers provided, validating, and running QA function on data provided
- Identify top 1-2 production onboarding decision trees which should be incorporated into the Rasa Chatbot
- Include an onboarding ID across all systems which allows tracking and promotion of client setups, and sends an onboarding tracker to clients
- Demonstrate functionality of the v1 prototype against applicable system requirements (before the end of Winter term)
- Collect feedback from key stakeholders
Expected Final Deliverable (Expected level of success)
- Complete the v2 prototype
- Integrate workflow with reference data applications to pre-validate entry fields – Rest APIs with HTTPS based applications
- Incorporate 1-2 pilot decision trees into RASA chatbot to facilitate accelerated intuitive onboarding
- Implement observability view and APIs for tracking.
- Integrate end to end onboarding ID as core onboarding ID
- Launch production version of Chatbot with existing features which should work seamlessly with underlying COBRA application and partner applications
Stretch Goal Opportunities: (High level of success)
- Incorporate Chatbot as primary interface for onboarding process
Below are the skills needed for this project. Students with the following relevant skills and interest, regardless of major, are encouraged to apply! This is a team based multidisciplinary project. Students on the team are not expected to have experience in all areas, but should be willing to learn and will be asked to perform a breadth of tasks throughout the two semester project.
NLU / Chatbot (2 Students)
Specific Skills: Applied project experience in utilizing NLU (Natural Language Understanding)
EECS 281(or equivalent) is required
Specific AI coursework would be extremely beneficial
Likely Majors: CS, DATA
Data Science (1 Student)
Specific Skills: Data set characterization and modeling, ability to develop/implement a wide variety of techniques
Willingness to quickly develop new technical skills as required by the project – must have general coding skills
EECS 281(or equivalent) is required
Likely Majors: DATA, CS
General Coding (2 Students)
Specific Skills: General programming skills, good software engineering practice and design
EECS 281 (or equivalent) is required, experience in full stack development a plus
Likely Majors: CS, DATA, BBA/CS
Additional Desired Skills/Knowledge/Experience
Strong candidates will have familiarity or experience with some of the following items, and a positive attitude to learn what is necessary, as the project gets underway.
- Interest in and general knowledge of Commercial Banking
- Successful team-based project experience
- Excellent interpersonal skills and the willingness to work hard
- Project Management utilizing Agile/Scrum
- Experience in business process analysis, customer/client interviewing
- Practical Experience with any/most of our tech stack
- Chatbots, Java, Python, NLU, NoSQL database, Spring Boot, Rest APIs, HTTPS based applications. Be sure to address this on your experience and interest form
- Note – it is unlikely that any student would be fully competent in the entire tech stack before the project. Significant individual training effort is expected and required
- Practical experience implementing predictive analytics in a complex data environment
Sponsor Mentor
Manish Rawat
Executive Director of Software Development
Manish is a senior technology leader with experience in managing and driving transformation programs and delivery teams in the financial domain. He has worked across major financial firms in the fintech domain for the better part of a 17 year career, focusing on application development, system architecture, data processing, data analytics, BI, big data, public/private cloud and user experience.
Executive Mentor
Todd Ippen
Executive Director, Global Technology
Todd is based in Chicago, Illinois and has been with the firm for over 24 years, fulfilling many roles from application development to multi-year program management involving architecture required to support numerous lines of businesses and products. Mr. Ippen is presently the Head of Loan Servicing, Digital Loans, and Collateral Technology. In addition, Mr. Ippen was responsible for the technical build and roll-out of the firm’s strategic loan platform to international markets in Europe, Latin America, and Asia. Outside of his day-to-day activities, Mr. Ippen is the JP Morgan Captain for University of Michigan recruiting, and is a member of two Chicago Technology Leadership Work streams (Recruiting & Global Innovation). Mr. Ippen is also the Chicago Tech Center University Recruiting Lead for all College Entry Level Software Engineering Programs (Internships and Full Time). In his free time, Mr. Ippen enjoys spending time with his wife and two children, travelling, boating, skiing, and attending various sporting activities.
Faculty Mentor
Vineet R. Kamat
John L. Tishman Family Professor of Construction Management and Sustainability
Vineet is a Professor of Civil and Environmental Engineering at the University of Michigan. His group researches methods to enable effective human-robot work collaboration in the construction, operation, and maintenance of civil infrastructure and the built environment. Their research has developed several licensable technologies that support automation and robotics, including modeling techniques that help on-site construction robots with autonomous decision making.
Weekly Meetings: During the winter 2025 semester, the JPMC team will meet on Tuesdays 3:30 – 5:30pm in EECS 1008.
Work Location: This project will take place on campus in Ann Arbor, with remote access to JPMorgan systems during Winter 25/Fall 25. All project team members are required to participate in the JPMorgan summer 2025 internship program based in their Chicago, IL office.
Course Substitutions: CE MDE, ChE Elective, CS Capstone/MDE, Data Science MDE/Capstone, EE MDE, CoE Honors, SI Elective/Cognate
Citizenship Requirements: Students selected for this team must have the right work in the U.S.A indefinitely, without sponsorship. All student team members are required to participate in JPMC 2025 summer internship program in Chicago, IL.
IP/NDA: Students will sign an IP and NDA agreement that is unique to JPMC.
Summer Project Activities: Summer 2025 Internships will be located in Chicago, Illinois. They are guaranteed and required for all students who match to this project team. Every student who accepts an offer to join this project team must also participate in the summer internship with JP Morgan. The approximate dates of the Internship are June 2nd – August 8, 2025
- All project students must participate in the JPMorgan summer internship program, and will be based in Chicago, Illinois
- All students must
- Have the right to work in the United States indefinitely without sponsorship
- Have cumulative University of Michigan GPA > 3.0
- Pass a background and drug test
MDP project offer letters will include required dates, compensation, and other conditions of the internship. Students will have 10 days to accept or reject their combined MDP/JPMC offer
Learn more about the expectations for this type of MDP project