# Fraud detection with Neo4j

> Fraud detection with Neo4j - Build a fraud detection pipeline using Neo4j for storing and querying a
> knowledge graph.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-06T18:17:09.585135+00:00` (UTC).

## Primary page

- [Fraud detection with Neo4j](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/time-series/fraud-detection.html): Full documentation for this topic (HTML).

## Related documentation

- [Developer documentation](https://docs.datarobot.com/en/docs/api/index.html): Linked from this page.
- [Developer learning](https://docs.datarobot.com/en/docs/api/dev-learning/index.html): Linked from this page.
- [AI accelerators](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/index.html): Linked from this page.
- [Time series and specific use cases](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/time-series/index.html): Linked from this page.

## Documentation content

[Access this AI accelerator on GitHub](https://github.com/datarobot-community/ai-accelerators/tree/main/use_cases_and_horizontal_approaches/datarobot-neo4j-knowledge-graph-for-fraud-detection)

This accelerator demonstrates how to build a fraud detection pipeline using Neo4j and DataRobot. Use Neo4j to store and query a knowledge graph of clients, loans, addresses, and more. Then, use DataRobot to build a predictive model with graph-based features. The accelerator contains multiple notebooks. The first notebook walks through installing a Neo4j 4.4.11 instance, loading a Neo4j database, and uploading a dump file with the CLI. The second notebook outlines how to extract graph data into training and holdout CSVs, upload training data to DataRobot, and build a classification model for scoring.