# BigQuery ML Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/bigquery-ml
> Markdown URL: https://aitinkerers.org/technologies/bigquery-ml.md
> Technology record last updated: 2026-02-24T13:28:54Z
> Generated: 2026-08-26T12:20:01Z

Train and run machine learning models directly on your petabyte-scale data using standard GoogleSQL, eliminating data movement and democratizing AI.

BigQuery ML is the integrated machine learning service that empowers data analysts (SQL practitioners) to build, train, and evaluate models directly within the data warehouse: no Python or external ML frameworks required. You execute model creation and prediction using simple GoogleSQL statements, like `CREATE MODEL` and `ML.PREDICT`. This approach keeps your data in BigQuery, accelerating development and model iteration for core use cases like Linear Regression, K-Means Clustering, and Time Series forecasting (ARIMA). For advanced needs, it integrates seamlessly with Vertex AI, allowing for MLOps management and access to powerful remote models like DNNs and Boosted Trees.

- Official technology site: https://cloud.google.com/bigquery
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Vibe✓ : Agentic Street-Level Stress Detection with Gemini and Vertex AI](https://nyc.aitinkerers.org/talks/rsvp_jmM5cVIBnT4)

This talk walks through the development of a real-time, cloud-native system for analyzing stress conditions across New York City using live CCTV footage. The system built using Angular and Google Cloud’s AI stack: Vertex AI, Gemini, BigQuery ML, together with Firebase app hosting, captures 940 concurrent camera streams and performs context-aware analysis through a Gemini-powered multimodal agent. Each camera is mapped to dynamically generated borough zones based on Voronoi tessellation, enabling location-specific metrics. The project spans five phases: 1. Multimodal vision analysis using Gemini for stress detection, with adaptive confidence thresholds. 2. A hybrid ML pipeline using Vertex AI and rule-based logic to classify high-risk conditions with 85%+ accuracy. 3. Time-series forecasting with BigQuery ML (ARIMA_PLUS) to detect seasonal patterns and enable pedestrian-aware predictive routing. 4. Event-driven, serverless infrastructure using Firebase Functions to support six-tier adaptive monitoring windows. 5. Live deployment with Firebase Hosting and GitHub Pages to ensure demo reliability and real-time updates. The demo includes a live analytics dashboard showing violation forecasts and real-time confidence scores for each camera zone. Each camera stream is sampled adaptively based on stress levels, and the backend is built for continuous training and edge-case reinforcement.

- Event context: Building AI Agents with Google Cloud AI — 2025-06-25 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_jmM5cVIBnT4

## Related Technologies

- [Cloud Vision AI](https://aitinkerers.org/technologies/cloud-vision-ai) ([Markdown](https://aitinkerers.org/technologies/cloud-vision-ai.md)) — 1 public demo
- [Firebase Functions](https://aitinkerers.org/technologies/firebase-functions) ([Markdown](https://aitinkerers.org/technologies/firebase-functions.md)) — 2 public demos
- [Google Maps API](https://aitinkerers.org/technologies/google-maps-api) ([Markdown](https://aitinkerers.org/technologies/google-maps-api.md)) — 3 public demos
- [Vertex AI](https://aitinkerers.org/technologies/vertex-ai) ([Markdown](https://aitinkerers.org/technologies/vertex-ai.md)) — 31 public demos