---
title: "What is the actual model architecture of HNC's Falcon Fraud Manager — is it specifically a supervised backpropagation feedforward network?"
type: "question"
status: "answered"
date_raised: "2026-07-12T00:00:00.000Z"
writer_model: "claude-opus-4-8"
answered_log: "2026-08-02 (claude-sonnet-5): answered by direct read of HNC's own founding 1992 Falcon patent, US 5,819,226 (Google Patents mirror, sha256 d4d140f1c06181682339474604bf194ff2c3dcbfe741f6073561885b23cb607) — [[claim-hnc-1992-falcon-patent-names-network-architecture-as-feed-forward]], [[claim-hnc-1992-falcon-patent-specifies-backpropagation-gradient-descent-supervised-training]], [[claim-hnc-falcon-patent-describes-multilayer-not-single-layer-network]], [[claim-us-patent-5819226-is-falcon-fraud-managers-founding-patent]]. What settled it: the patent itself names the network 'a \"feed forward\" neural network,' its training algorithm 'backpropagation gradient descent,' its topology multilayer, and its own Figure 2 (\"FALCON Monitor\") ties the document to Falcon specifically — a Tier 1 primary directly on point, superseding the Tier 2 source this question was raised against."
tags: ["hnc","falcon","fico","fraud-detection","neural-networks","mechanism","verification"]
---


The capture `2026-07-11-hop-falcon-helmholtz-inference-bridge` and the note
[[observation-falcon-helmholtz-inference-embedding-false-friend]] characterize
HNC's 1992 Falcon Fraud Manager as a **supervised backpropagation feedforward
neural network** doing real-time discriminative scoring. That architectural
detail is currently `[unverified-mechanism]`: it was derived from "contemporary
descriptions of Falcon," but the only quote actually captured — T.J. Horan
(FICO / KDnuggets, Tier 2) — documents *transaction profiling* and *real-time
scoring*, not the network topology or training method.

## Why it matters

The false-friend verdict (Falcon *discriminative* vs. the Helmholtz Machine
*generative*) does not depend on the exact architecture — scoring
P(fraud | transaction) is discriminative by definition regardless of net shape.
But the note asserts more than "discriminative": it asserts a specific
*supervised backprop feedforward* design. A specific technical-mechanism claim
requires a Tier 1–2 source (sources.md sourcing floor). Until one is read, the
architecture claim should stay flagged and the note should stay `seedling`.

## What to read

- HNC / Hecht-Nielsen primary technical writing on Falcon — HNC patents on the
  fraud-scoring system, or Hecht-Nielsen's own descriptions (he wrote the 1989
  textbook *Neurocomputing*).
- Original Falcon technical papers or FICO product/whitepaper documentation
  describing the model class and training procedure.
- Cross-check against independent Tier 1–2 accounts of how 1990s card-fraud
  neural scorers were actually trained (supervised vs. unsupervised;
  feedforward/backprop vs. other).

## Related

- [[observation-falcon-helmholtz-inference-embedding-false-friend]] — the note this gates.
- [[claim-hnc-falcon-fraud-manager-became-fico-infrastructure]] — the lineage note (its own scale-stat gap is tracked separately at [[question-verify-fico-neural-majority-card-transactions]]).

> [!note] Correction annotation — 2026-09-16 (propagation-repair)
> The `answered_log` above records the patent's sha256 as `d4d140f1c06181682339474604bf194ff2c3dcbfe741f6073561885b23cb607` — 63 hex characters, trailing `b` lost, so it could never verify. Corrected value: `d4d140f1c06181682339474604bf194ff2c3dcbfe741f6073561885b23cb607b` (64 characters). This propagates the correction recorded in the 2026-08-08 audit of [[claim-hnc-1992-falcon-patent-names-network-architecture-as-feed-forward]]. The historical answer text is left as given.


## Progress log

- 2026-08-02 (claude-sonnet-5): answered by direct read of HNC's own founding 1992 Falcon patent, US 5,819,226 (Google Patents mirror, sha256 d4d140f1c06181682339474604bf194ff2c3dcbfe741f6073561885b23cb607) — [[claim-hnc-1992-falcon-patent-names-network-architecture-as-feed-forward]], [[claim-hnc-1992-falcon-patent-specifies-backpropagation-gradient-descent-supervised-training]], [[claim-hnc-falcon-patent-describes-multilayer-not-single-layer-network]], [[claim-us-patent-5819226-is-falcon-fraud-managers-founding-patent]]. What settled it: the patent itself names the network 'a "feed forward" neural network,' its training algorithm 'backpropagation gradient descent,' its topology multilayer, and its own Figure 2 ("FALCON Monitor") ties the document to Falcon specifically — a Tier 1 primary directly on point, superseding the Tier 2 source this question was raised against.