Skip to content

Improving Public Services with AI + Machine Learning

We use artificial intelligence and machine learning to support employees of the cantonal administration and deliver better public services. We view AI as one of many tools for digital transformation.

Team Data at the Office for Statistics and Data of the Canton of Zurich is a data science competence center. Our AI pilot projects help the cantonal administration build expertise in using AI.

Our pilot projects explore whether machine learning can solve specific problems in our business processes. Together with partners in the cantonal administration, we develop prototypes and proofs of concept to validate potential solutions. Learn more about how the canton works with AI.

We share experiences, code, and data from our pilot projects here on GitHub whenever possible. We welcome feedback—email us or open issues or pull requests in the relevant repositories.

Pilot Projects and Prototypes

Information & Knowledge Management

  • TranscriboZH Audio Transcription: Transcribe any audio or video file. Edit and view transcripts in a standalone HTML editor.
  • Hybrid Search: Intelligent search application for large document collections.
  • Document Research Tool: Conduct intelligent research across document collections using hybrid search and LLMs.
  • Deep Research: Powerful, automated research and analysis across your own document collections.
  • AI Chat: A locally run LLM chat application with document processing capabilities.
  • Semantic Search Evaluation Tool: A framework for evaluating semantic search across custom datasets, metrics, and embedding backends.
  • Hybrid Search Evaluation Tool: A framework for benchmarking embedding models in hybrid search scenarios (BM25 + vector search). Measure MRR@K, Hit@K, embedding latency, and memory consumption. Bring your own data or use MTEB-compatible datasets.
  • Named Entity Recognition (archived): A NER framework tailored to administrative use cases.

Accessibility & Language Simplification

Open Government Data (OGD)

  • OGD AI Analyzer: Analyze the quality of a DCAT metadata catalog.
  • OGD AI Metafairy: Create high-quality dataset descriptions.
  • OGD AI Search: Search your OGD metadata catalog using semantic, lexical, and multilingual search.

Voting & Elections

  • Plausi App: Predict votes and detect anomalies using R.

Our GitHub Organizations

Pinned Loading

  1. audio-transcription audio-transcription Public

    Transcribe any audio or video file. Edit and view your transcripts in a standalone HTML editor.

    Python 99 27

  2. simply-simplify-language simply-simplify-language Public

    Use machine learning to make your institutional communication more understandable and inclusive.

    Python 48 9

  3. semantic-search-eval semantic-search-eval Public

    A framework for evaluating semantic search across custom datasets, metrics, and embedding backends.

    Python 40 7

  4. hybrid-search-eval hybrid-search-eval Public

    A framework for benchmarking embedding models in hybrid search scenarios (BM25 + vector search) using Weaviate.

    Python 40 2

  5. zix_understandability-index zix_understandability-index Public

    Measure how understandable a German text is.

    Jupyter Notebook 12 3

  6. plausi plausi Public

    Detect Anomalies in Vote-Results - powered by Statistics & Machine Learning

    R 4 2

Repositories

Showing 10 of 19 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…