Free tools Windows power users keep installed
One-click scans. No signup required.
iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
FraudLens is a 2026 hackathon project that treats a suspicious transaction alert as the start of an investigation, not a verdict from a fraud classifier. It uses TigerGraph to trace transaction and customer relationships, gathers evidence for and against fraud, and applies a separate policy engine to determine what action is allowed. Its creators report a 20-case benchmark, but the published account does not establish independent validation or bank deployment.
What FraudLens investigates
FraudLens was built for Goa Hackerhouse 2026 using a bank transaction dataset, closed investigation history, and 20 open alerts, according to the project article by Yash Fadadu and Team TrustMeBro, published September 24, 2026. Its central premise is that a risk score should prompt an investigation rather than settle the case.
For each alert, the system examines the transaction, card, and customer relationships, then gathers transaction history and graph context. It checks for known fraud patterns, looks for an innocent explanation, retrieves similar closed cases, and assesses both probability and uncertainty. It can request more evidence when that evidence could change the recommended action. A policy engine governs the available actions and approval routes, after which the case is written to TigerGraph and read back for verification.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
The questions this approach is meant to answer include whether a purchase fits the customer’s usual spending, whether a device appears across other cards, how similar past cases ended, whether an innocent explanation fits, and whether contacting the customer before blocking a card is worthwhile.
#1 Best Overall
How the architecture divides responsibility
The project assigns different jobs to the graph, agent, language model, and policy engine. In the team’s stated design, TigerGraph and GSQL store and traverse relationships; a LangGraph agent manages investigation state and choices about evidence gathering; an LLM handles planning and prose; and a deterministic policy engine controls actions and approval routing.
The team says the LLM cannot approve an action and that the API rechecks policy requirements. That is a description of the project’s intended safeguards, not an independent security audit or a guarantee that every possible path is safe.
Graph entities and time-ordered transactions
The graph models customers, cards, and transactions, alongside shared-origin entities such as device profiles, email domains, and billing regions. It also represents case-memory entities: FraudCase, Evidence, EvidenceRequest, and ActionDecision. A NEXT edge links each card’s transactions in time order.
The project article reports approximately 26 installed GSQL queries spanning alert anchoring and context, pattern detection, relationship discovery, graph algorithms, case memory, and write-back. Each read query requires a cutoff time, intended to prevent an investigation from seeing transactions that occurred after the case’s relevant point in time.
Rank #3
- Commemorate Tiger Woods' 25-year journey with a billiant, fully illustrated table book from Sports Illustrated
- Sturdy build and construction. The hand bounded green leather hardcover gives it the perfect vintage look and durability
- Its polished aesthetic perfectly aligns with the golf theme of this book, lending an elegant touch to your bookshelf or coffee table.
- 232 pages full of iconic vibrant photos and some of the best written coverage of Woods’s career
- Beautiful Stories, a good read, and great photographies, the ideal gift book for any Tiger fan
Evidence, conclusions, and write-back
FraudLens stores evidence with its source and the query that produced it, separately from the agent’s conclusions. The project describes read-only investigation tools and a write path the model cannot call directly. After writing a case bundle, the system reads it back and compares counts and a hash to check that the stored bundle matches what it intended to write.
What the project reports from its benchmark
Team TrustMeBro reports the following results for its described 20-case benchmark. These are project-reported figures, not independent performance measurements.
| Measure | Project-reported result |
|---|---|
| Answer validation | 20 of 20 cases passed the answer validator |
| Graph write-back | 20 of 20 cases were written and verified by read-back |
| Verdicts | 7 fraud, 12 legitimate, and 1 uncertain |
| Suspicious activity reports | 6 generated |
| Graph queries per case | 21–34 |
The project article gives no independent validation results or evidence of production deployment at a bank. The benchmark therefore describes what the team reports for its own cases; it does not establish how the system would perform on other institutions’ data, at operational scale, or against independently adjudicated outcomes.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →What the implementation challenges reveal
Generic devices can create misleading links
The team reports that generic device profiles produced false connections: an “unknown | unknown | unknown” profile was associated with 1,011 customers, while a common Windows + Chrome profile was associated with 842. Requiring a more specific device profile reduced the project’s suspicious activity report count to 6 of 20 cases. This illustrates why a graph connection is a lead to examine, not proof that two accounts share a fraudster.
Data loading and query behavior need verification
The project account also describes live-instance issues involving reserved GSQL words, Boolean defaults, file-loading behavior, and prefixed query-output fields. An initial bulk load omitted about 14,000 transactions; comparing graph vertex counts with source-file counts exposed the gap. For a system that relies on relationship traversal, checking ingestion completeness is part of the investigation’s reliability, not a one-time setup detail.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.How to interpret the project
FraudLens is best understood as an architecture demonstration for graph-assisted fraud investigation. Its distinctive idea is to make relationships, counter-evidence, time boundaries, evidence provenance, and action controls explicit in the workflow. The reported benchmark suggests the team exercised an end-to-end pipeline, including answer validation and graph read-back, but it does not establish production readiness or independently measured fraud-detection accuracy.
For readers evaluating similar systems, useful questions include whether each finding can be traced to its source and query, how the system handles evidence against suspicion, whether historical context is constrained by an enforced cutoff, who approves consequential actions, whether stored case records are verified, and whether performance has been independently evaluated.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
