Memgraph in fraud detection

pages/deployment/benchmarking-memgraph.mdx

@@ -62,7 +62,7 @@ While `mgbench` gives you full control over benchmarking and produces raw result
 analyzing performance metrics at scale can be time-consuming. That’s why we created
 [**Benchgraph**](https://github.com/memgraph/benchgraph)—a companion visualization tool for `mgbench`.
 
-![](/pages/memgraph-in-production/benchmarking-memgraph/benchgraph-snippet.png)
+![](/pages/deployment/benchmarking-memgraph/benchgraph-snippet.png)
 
 Benchgraph is not required to use `mgbench`, but it offers a **convenient way to visualize and explore**
 benchmark results across a variety of run conditions:

pages/deployment/workloads.mdx

@@ -47,12 +47,16 @@ Scale your write throughput while keeping up with fast-changing, high-velocity g
 ### [Memgraph in GraphRAG use cases](/deployment/workloads/memgraph-in-graphrag)
 Learn how to optimize Memgraph for Retrieval-Augmented Generation (RAG) systems using graph data.
 
+### [Memgraph in supply chain](/deployment/workloads/memgraph-in-supply-chain)
+Use Memgraph for root-cause analysis, what‑if impact analysis, constraint-based pathfinding, and many more other use cases across your supply chain network.
+
+### [Memgraph in fraud detection](/deployment/workloads/memgraph-in-fraud-detection)
+Deploy Memgraph for real-time scoring, fraud ring discovery, and investigator workflows at scale.
+
 ## 🚧 Guides in construction
 - Memgraph in transactional workloads
 - Memgraph in analytical workloads
 - Memgraph in mission critical workloads
-- Memgraph in supply chain use cases
-- Memgraph in fraud detection use cases
 
 <Callout type="info">
 If you'd like to help us **prioritize** this content, feel free to reach out on [Discord](https://discord.gg/memgraph)! 

pages/deployment/workloads/_meta.ts

@@ -2,4 +2,7 @@ export default {
  "memgraph-in-cybersecurity": "Memgraph in cybersecurity",
  "memgraph-in-graphrag": "Memgraph in GraphRAG use cases",
  "memgraph-in-high-throughput-workloads": "Memgraph in high-throughput workloads",
+ "memgraph-in-mission-critical-workloads": "Memgraph in mission critical workloads",
+ "memgraph-in-supply-chain": "Memgraph in supply chain",
+ "memgraph-in-fraud-detection": "Memgraph in fraud detection",
 }

pages/deployment/workloads/memgraph-in-cybersecurity.mdx

@@ -50,7 +50,7 @@ Here's why Memgraph is a great fit for cybersecurity use cases:
  While many graph databases **max out around 1,000 events per second**, Memgraph can handle **up to 50x more** 
  (see image below), making it ideal for **high-velocity security event processing**.
 
- ![](/pages/memgraph-in-production/benchmarking-memgraph/realistic-workload.png)
+ ![](/pages/deployment/benchmarking-memgraph/realistic-workload.png)
 
 - **Non-blocking reads and writes with MVCC**: Built on multi-version concurrency control (MVCC), 
  Memgraph ensures that **security event ingestion doesn't block threat analysis** and **analysis doesn't block ingestion**,

pages/deployment/workloads/memgraph-in-fraud-detection.mdx

@@ -0,0 +1,149 @@
+---
+title: Memgraph in fraud detection
+description: Suggestions on how to bring your Memgraph to production in fraud detection and anti-abuse use cases.
+---
+
+import { Callout } from 'nextra/components'
+import { CommunityLinks } from '/components/social-card/CommunityLinks'
+
+# Memgraph in fraud detection
+
+<Callout type="info">
+Before diving into this guide, we recommend starting with the [Deployment best practices](/deployment/best-practices)
+page. It provides foundational, use-case-agnostic advice for deploying Memgraph in production.
+
+This guide builds on that foundation, offering additional recommendations tailored to fraud detection and anti-abuse workloads.
+In cases where guidance overlaps, consider the information here as complementary or overriding, depending on the
+unique needs of your use case.
+</Callout>
+
+## Is this guide for you?
+
+This guide is for you if you're building real-time **fraud detection**, **anti-money laundering (AML)**, or **account abuse** systems.
+You'll benefit from this content if:
+
+- You need to **detect anomalies in real time** across transactions, devices, identities, and merchants.
+- You want to uncover **multi-hop fraud rings** (e.g., money mules, collusion networks, synthetic identities) and **account takeover cascades**.
+- You plan to run **what‑if tests** to evaluate new rules, thresholds, and investigation workflows before rollout.
+- You ingest high-velocity events from **payments/auth logs/identity services** and require consistent read performance while updates stream in.
+- You need to correlate evidence across systems for **investigation and case management**.
+
+## Why choose Memgraph for fraud detection?
+
+- **In-memory architecture**: Consistent, predictable response times for scoring, alerting, and investigator tooling.
+- **Graph algorithms (MAGE)**: Use community detection, node similarity, centralities, and more to **infer hidden structure and risk signals** (e.g., collusion clusters, mule networks, synthetic identities). Explore the [available algorithms](/advanced-algorithms/available-algorithms).
+- **Streaming/dynamic algorithms**: Keep results fresh on **high‑velocity data** with online/dynamic algorithms that update incrementally (e.g., online centralities). See [dynamic graph algorithms](/advanced-algorithms/available-algorithms#dynamic-graph-algorithms-enterprise).
+- **GNNs and ML on graph topology**: Leverage graph-native topology for **GNNs** (e.g., node classification, link prediction) and combine **embeddings** with graph algorithms to improve fraud detection accuracy over tabular‑only baselines.
+
+
+## What is covered?
+
+The suggestions for fraud detection workloads complement several key sections in the
+[general suggestions guide](/deployment/best-practices). These sections offer important context and
+additional best practices tailored for performance, stability, and scalability in production:
+
+- [Choosing the right Memgraph flag set](/deployment/best-practices#choosing-the-right-memgraph-flag-set) 
+ Configure flags for schema access.
+
+- [Choosing the right Memgraph storage mode](/deployment/best-practices#choosing-the-right-memgraph-storage-mode) 
+ Select between transactional durability and multithreaded ingestion for your workload.
+
+- [Optimizing fraud detection](#optimizing-fraud-detection) 
+ Use deep path traversals, map properties, and nested indices.
+
+- [Enterprise features you might require](#enterprise-features-you-might-require) 
+ Secure multi-user environments and ensure governance.
+
+## Choosing the right Memgraph flag set
+
+If you plan to power natural-language interfaces for investigators (see GraphRAG below), enable constant-time schema retrieval:
+
+```bash
+--schema-info-enabled=true
+```
+
+This drastically reduces time to provide schema to an LLM, improving responsiveness.
+
+## Choosing the right Memgraph storage mode
+
+Most finance and fraud workloads are inherently **transactional** (safety-critical decisions, auditability, recoverability). As a default,
+we recommend running in `IN_MEMORY_TRANSACTIONAL` mode to ensure **ACID guarantees**, support for **replication/HA**, and **WAL/snapshot** durability.
+
+Consider `IN_MEMORY_ANALYTICAL` only for specialized pipelines focused on **bulk/multithreaded ingestion** and **read-only analytics/simulations** where transactional rollback isn’t required.
+Another suitable flow for using analytical is during import, after which the user will switch to `IN_MEMORY_TRANASCTIONAL` mode for ensuring data consistency during the batch update process day-to-day.
+
+Learn more about storage modes in the [Storage memory usage](/fundamentals/storage-memory-usage#storage-modes) documentation.
+
+## Enterprise features you might require
+
+- **Role-based and label-based access control (RBAC/LBAC)** 
+ Ensure least-privilege access across analysts, SOC teams, and external partners. See
+ [Role-based access control](/database-management/authentication-and-authorization/role-based-access-control).
+
+- **Replication and high availability** 
+ Keep scoring and investigations online with leader–replica setups and automatic failover. See
+ [High availability](/clustering/high-availability) and [Replication](/clustering/replication).
+
+- **Multi-tenancy** 
+ Isolate per product, region, or use case. See [Multi-tenancy](/database-management/multi-tenancy).
+
+- **Single sign-on (SSO) for Memgraph Lab** 
+ Streamline secure access for your fraud investigators and stakeholders. See [Single sign-on](/memgraph-lab/features/single-sign-on).
+
+- **Audit logs** 
+ Track access and changes for compliance and investigations. See [Audit log](/database-management/enabling-memgraph-enterprise#audit-log).
+
+- **Query sharing for collaboration** 
+ Enable investigators to share queries and findings seamlessly. See [Sharing features](/database-management/enabling-memgraph-enterprise#sharing-features).
+
+## Working with fraud detection
+
+There are three complementary ways to build fraud detection on Memgraph:
+
+### 1) Basic pattern matching in Cypher
+Use Cypher to encode rules and patterns directly over the graph:
+- Variable‑length paths for multi‑hop patterns (e.g., mule chains, shared devices)
+- Property/time filters for velocity and windowing
+- Negative patterns (absence of expected relationships)
+
+```cypher
+// Example: shared device across multiple accounts in a short window
+MATCH (d:Device)<-[:USED_DEVICE]-(a:Account)-[:PERFORMED]->(tx:Txn)
+WHERE tx.ts >= $from AND tx.ts < $to
+WITH d, collect(DISTINCT a) AS accounts
+WHERE size(accounts) >= $minAccounts
+RETURN d, accounts;
+```
+
+### 2) Graph algorithms (MAGE)
+Compute risk signals by scoring topology. Commonly useful algorithms include:
+- [Katz centrality](/advanced-algorithms/available-algorithms/katz_centrality)
+- [Degree centrality](/advanced-algorithms/available-algorithms/degree_centrality)
+- [Community detection](/advanced-algorithms/available-algorithms/community_detection)
+- [PageRank](/advanced-algorithms/available-algorithms/pagerank)
+- [Betweenness centrality](/advanced-algorithms/available-algorithms/betweenness_centrality)
+- [Node similarity](/advanced-algorithms/available-algorithms/node_similarity)
+
+Browse more in [Available algorithms](/advanced-algorithms/available-algorithms). Many also have online/dynamic variants (e.g., [pagerank_online](/advanced-algorithms/available-algorithms/pagerank_online), [katz_centrality_online](/advanced-algorithms/available-algorithms/katz_centrality_online)) for high‑velocity data.
+
+### 3) Machine learning on graphs
+Leverage graph structure and embeddings to train models:
+- Supervised GNNs: [GNN node classification](/advanced-algorithms/available-algorithms/gnn_node_classification), [GNN link prediction](/advanced-algorithms/available-algorithms/gnn_link_prediction)
+- Unsupervised embeddings: [node2vec](/advanced-algorithms/available-algorithms/node2vec), [node2vec_online](/advanced-algorithms/available-algorithms/node2vec_online)
+
+Combine ML features (embeddings, graph algorithm scores, rule outputs) into your fraud scoring pipeline to maximize precision/recall.
+
+
+## Interact with your fraud graph using GraphRAG
+
+Enable natural-language interaction for triage and investigations with GraphRAG and GraphChat in Memgraph Lab.
+This helps non-technical stakeholders quickly ask: “Is user X linked to known fraud rings?” or “Show connections between these accounts in the last 30 days.”
+
+- See: [Memgraph in GraphRAG use cases](/deployment/workloads/memgraph-in-graphrag)
+- Include constant-time schema retrieval in your pipeline:
+
+```cypher
+SHOW SCHEMA INFO;
+```
+
+<CommunityLinks/> 

pages/deployment/workloads/memgraph-in-graphrag.mdx

@@ -43,7 +43,7 @@ Here's what makes Memgraph a perfect fit for GraphRAG:
 ## What is covered?
 
 The suggestions for GraphRAG use cases **complement** several key sections in the 
-[general suggestions guide](/memgraph-in-production/general-suggestions). These sections offer important context and
+[general suggestions guide](/deployment/best-practices). These sections offer important context and
 additional best practices tailored for performance, stability, and scalability in GraphRAG systems:
 
 - [Hardware sizing](#hardware-sizing)

pages/deployment/workloads/memgraph-in-high-throughput-workloads.mdx

@@ -45,7 +45,7 @@ Here's why Memgraph is a great fit for high-throughput use cases:
  While many graph databases **max out around 1,000 writes per second**, Memgraph can handle **up to 50x more** 
  (see image below), making it ideal for **high-velocity, write-intensive workloads**.
 
- ![](/pages/memgraph-in-production/benchmarking-memgraph/realistic-workload.png)
+ ![](/pages/deployment/benchmarking-memgraph/realistic-workload.png)
 
 - **Non-blocking reads and writes with MVCC**: Built on multi-version concurrency control (MVCC), 
  Memgraph ensures that **writes don’t block reads** and **reads don’t block writes**, allowing each to scale independently.
@@ -71,7 +71,7 @@ Here's why Memgraph is a great fit for high-throughput use cases:
 ## What is covered?
 
 The suggestions for high-throughput workloads **complement** several key sections in the 
-[general suggestions guide](/memgraph-in-production/general-suggestions). These sections offer important context and
+[best practices guide](/deployment/best-practices). These sections offer important context and
 additional best practices tailored for performance, stability, and scalability in high-throughput systems:
 
 - [Choosing the right Memgraph flag set](#choosing-the-right-memgraph-flag-set) <br />