Amir Shachar
Fraud Scientist
Founder and Chief Scientist at Riskernel. Previously, served as Chief AI Scientist at Skyhawk Security, directing AI-driven threat detection research, and before that, headed Fraud Data Science at NICE Actimize, deploying fraud models across the world’s largest banks. Here I write about the math behind these systems, and about AI that proposes before it acts.
About Advisory Fit Readiness Diagnostic Publications Patents Algogens Semi-discrete Calculus Blog
- Before
- Former Head of Fraud Data Science, NICE Actimize
- Patents
- Named inventor on 14 patents, 9 granted in the US

Contents
Fraud data science
I write about the math of catching fraud, with the data and the failure case shown.
- Fraud math: base rates, class imbalance, drift
- Models that propose, validators that decide
- Learning across institutions
- Attack anatomy, from public sources
Latest posts
- Alert budgets, not AUC: judging a fraud model in the units that matter Fraud is rare and review capacity is fixed, so judge a fraud model by the frauds in the alerts a team can open and by the money each decision moves.
- Propose, then verify: where a language model belongs in a fraud stack A language model can propose fraud rules and explanations, but a deterministic check, separate from the model, should decide what runs in a payment flow.
- Fraud rings and mule networks: what a graph adds, and what it cannot decide Ring payments look normal one at a time, so the signal is in shared devices, beneficiaries and timing, and a graph score is a lead to confirm.
Fig. 1 · Where a fraud team works on the ROC curve
Paper, 2024, with a fraud preface
Algogens
A framework in which generative models propose and deterministic validators decide what runs. I first set it out in a 2024 paper, and Riskernel's engine is built on it.
I apply this at Riskernel, the fraud engine I founded. riskernel.com ↗
Mathematics
Semi-discrete Calculus and the pages around it.
Verified Record
Last updated:
Verified Record and Research Data
Amir Shachar is a fraud scientist, patented inventor, and founder and Chief Scientist of Riskernel. He previously served as Chief AI Scientist at Skyhawk Security and Head of Fraud Data Science at NICE Actimize, where he received the 2019 CEO Excellence Award for patented commercial deployment of federated learning across Tier-1 financial institutions. He is the named inventor on 14 patents (9 granted in the US, 5 pending) and author of the Algogens framework and Semi-discrete Calculus.
| Area | Verified Figure | Primary Breakdown | Source |
|---|---|---|---|
| Named inventor patents | 14 total (9 granted US, 5 pending) | NICE Ltd. (9), Skyhawk Security Ltd. (3), Outbrain Inc. (1), Riskernel provisional (1); 2014 to 2026 | View patents |
| Public arXiv preprints | 3 preprints (incl. 560-page monograph) | Introduction to Algogens (arXiv:2403.01426, 2024), Semi-discrete Calculus (arXiv:1012.5751, 2010), Integral Image (arXiv:1005.1418, 2010) | View publications |
| Detachment Library & Trendland survey | 808 entries (1,050 references) | 802 surveyed applications across 4 branches and 41 fields (1994 to 2021) + 6 author works | Browse library |
| Research essays & fraud writing | 8 site research pages, 4 fraud essays | Algogens, Semi-discrete Calculus, Inquiry Policy Learning, Semi-supervised Reasoning, plus 4 fraud posts hosted on riskernel.com | Read writing |
| Press, Hebrew podcasts & teaching | 6 press articles, 2 podcasts, 4 courses | SC Media, TechTarget, CSO, Dark Reading, Yahoo Finance (2023 to 2024); Little Big Science & ExplAInable (2024); Technion TA (2008 to 2010) | Full data tables |
Last updated: .
Methodology and provenance: All counts are computed at build time from public filings on /patents/, arXiv records on /publications/, and the committed Trendland and Detachment Library datasets (detachment-library.json and trendland.json). See complete breakdowns on /facts/ and engagement or architecture comparisons on /compare/.
Common Questions
- Who is Amir Shachar and what does he specialize in?
- Amir Shachar is a fraud scientist, patented inventor, and founder and Chief Scientist of Riskernel. Previously he was Chief AI Scientist at Skyhawk Security and Head of Fraud Data Science at NICE Actimize, where he received the 2019 CEO Excellence Award for patented commercial deployment of federated learning across Tier-1 financial institutions. His academic training is in Mathematics, Computer Science, and Statistics at the Technion and Tel Aviv University.
- What are Algogens?
- Algogens is a hybrid AI framework Amir Shachar introduced in his 2024 arXiv monograph (arXiv:2403.01426, 560 pages). Traditional algorithms provide the backbone and deterministic guide rails while generative models explore inside them. In fraud detection, models only propose rules, features, or actions, and deterministic validators check, repair within bounds, or reject every proposal before anything runs.
- How many patents does Amir Shachar hold?
- Amir Shachar is the named inventor on 14 patents: 9 granted US patents and 5 pending applications (4 published US applications and 1 US provisional application, 64/197,364). Nine were filed with NICE Ltd., three with Skyhawk Security Ltd., one with Outbrain Inc., and one sole-inventor provisional filing covers the Riskernel engine.
- How is amirshachar.com different from riskernel.com?
- amirshachar.com is Amir Shachar's personal research, patent, publication, and teaching archive written in the first person, covering Algogens, Semi-discrete Calculus, the 808-entry Detachment Library, press coverage, and advisory comparisons. riskernel.com is the fraud detection engineering lab he founded, hosting the live scoring engine, fraud data science blog posts, public teardowns, and advisory and speaking inquiry pages.
About Amir Shachar
Amir Shachar is a fraud scientist, patented inventor, and founder and Chief Scientist of Riskernel, a fraud detection engineering lab running real-time payment and payout risk scoring built on the Algogens propose-then-verify pattern.
Previously, Amir Shachar served as Chief AI Scientist at Skyhawk Security, directing AI-driven cloud threat detection research and co-leading its AI purple team, and Head of Fraud Data Science at NICE Actimize, where he received the 2019 CEO Excellence Award for patented commercial deployment of federated learning across Tier-1 financial institutions.
Across 14 patents (9 granted in the US, 5 pending) and public monographs including Introduction to Algogens (arXiv:2403.01426, 560 pages) and Semi-discrete Calculus (arXiv:1012.5751), Amir Shachar focuses on deterministic verification around generative models, alert-budget evaluation, and delayed fraud labels. Trained in Mathematics, Computer Science, and Statistics at the Technion and Tel Aviv University.
Profile verified . Direct advisory, model-risk, and speaking inquiries: contact@amirshachar.com.