Arizona State University builds Gemini-powered math support chatbot and AI enrollment propensity model on Google Cloud
Arizona State University (ASU) uses Google Cloud to support student learning and outreach. ASU Prep’s Archie chatbot uses Gemini to help middle and high school students solve math problems in real time by identifying errors, providing hints, and explaining problems. ASU EdPlus built an AI-powered platform that ingests enrollment and student success center audio, transcribes it, extracts insights, and combines it with web behavior data to predict enrollment likelihood.
- Organization
- Arizona State University
- Industry
- Education
- Location
- United States
- Published
- June 2026
Reported outcomes
4x
quantified impactQuality & accuracy
Strategic outcomes
Catalog median for quality & accuracy deployments: +90% across 282 reported metrics. Compare benchmarks →
Primary read
Use case focus
Showing 3 of 5
- 1Student support chatbot
- 2Enrollment propensity modeling
- 3Predictive analytics
- Improve student support in math.
- Better target enrollment outreach.
- Process large volumes of student interaction data securely and within compliance.
- Gemini powers the Archie math support chatbot with hint and error feedback.
- BigQuery is used to ingest and analyze large volumes of structured and unstructured data.
- ASU EdPlus built an AI-powered platform that converts audio recordings to text and uses a propensity model to predict enrollment likelihood from web behavior data.
- Students using Archie increased correct math answers by 6%.
- The enrollment propensity model was 4x more accurate than naive random guessing.
- Marketing campaigns using the model increased registrations by 52% compared with traditional lead scores.
Implementation partners2
Sources & evidence1
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?