Unit 02 · Chapter 5 · 15 min read

First-party misuse, merchant abuse, and feedback

Distinguish deception from service problems and build reliable labels.

A customer says the package never arrived. The carrier says delivered. The photo shows a door, but perhaps the wrong door. Risk work gets better when the analyst can hold more than one explanation at a time.

Separate misuse from ordinary disputes

First-party misuse involves a party making a deceptive claim about its own transaction or obligation. A mistaken memory, confusing descriptor, or delivery failure can look similar at first. Use evidence that addresses the disputed fact rather than assuming intent from a claim category.

Check order recognition, household use, fulfillment, cancellation, and prior communication. Preserve what remains unknown. A repeated claim pattern can justify review, but repetition alone does not establish deception. The customer may be dealing with a recurring merchant failure. Accurate classification improves both fraud controls and service quality.

Inside the mechanism. Ordinary service disputes, opportunistic misuse, merchant failure, and unauthorized payments can produce superficially similar refund requests. Keep the allegation, evidence, reason code, and final conclusion distinct. A customer who reports a real delivery failure is not proven abusive because they previously received a refund. Decisions should use the relevant facts and retain a correction path when the original classification was wrong.

A concrete example. A refund request or dispute can arise from delivery failure, confusion, product design, or deliberate deception. The label must reflect evidence about the actual cause. The rule flags 573 of 13,500 customer dispute records. Of those flags, 378 meet the synthetic target, giving 65.97% precision. It misses 95 target events. Under the stated cost assumptions, residual loss and operating friction total $19,613. The important result is the connection between the population, action, capacity, and outcome—not one isolated score.

When the assumption fails. All chargebacks become fraud labels regardless of reason or final result. Keep allegations, reviewed findings, commercial failures, and revised outcomes distinct. The following worked sequence shows the reference condition, a stress condition, and a response condition with explicit synthetic data. These are comparative assumptions, not measured causal effects.

Follow a worked case3 conditions · 36 figures

A refund request or dispute can arise from delivery failure, confusion, product design, or deliberate deception. The label must reflect evidence about the actual cause.

Separate misuse from ordinary disputes — the flow
Separate misuse from ordinary disputes Separate misuse from ordinary disputes — the flow Follow the sequence. Separate known facts from intent. Claim Record the disputed fact Evidence Test competing explanations Conclusion Separate known facts from intent
  1. ClaimRecord the disputed fact
  2. EvidenceTest competing explanations
  3. ConclusionSeparate known facts from intent
Follow the sequence. Separate known facts from intent. Chapter sources · Open image
Separate misuse from ordinary disputes — the distinction
Separate misuse from ordinary disputes Separate misuse from ordinary disputes — the distinction These concepts answer different questions. Read each definition in the context of the section. Service failure Merchant did not meet the promise Deceptive claim Evidence supports intentional misstatement
Service failure
  • Merchant did not meet the promise
Deceptive claim
  • Evidence supports intentional misstatement
These concepts answer different questions. Read each definition in the context of the section. Chapter sources · Open image
Delivery dispute
Separate misuse from ordinary disputes Delivery dispute Fictional teaching record. Claim needs investigation. Delivery dispute Illustrative data; not a real customer record or a prescribed policy. Carrier marked delivered One source of evidence Photo unmatched doorway Uncertainty remains Customer denies receipt Claim needs investigation The record may support more than one explanation
Fictional educational excerpt / Not for execution

Delivery dispute

Illustrative data; not a real customer record or a prescribed policy.

  1. Carriermarked delivered

    One source of evidence

  2. Photounmatched doorway

    Uncertainty remains

  3. Customerdenies receipt

    Claim needs investigation

The record may support more than one explanation

Fictional teaching record. Claim needs investigation. Chapter sources · Open image
Separate misuse from ordinary disputes — control and failure modes
Separate misuse from ordinary disputes Separate misuse from ordinary disputes — control and failure modes The record may support more than one explanation. The branches show why alternative designs fail. Control design Test the delivery evidence against the specific order. The record may support more than one explanation. Failure mode 1 Treat every dispute as dishonest. That ignores service failures. avoid Failure mode 2 Assume a status proves correct delivery. The destination still matters. avoid Failure mode 3 Ignore repeated merchant complaints. They may reveal a systemic issue. avoid
Control design

Test the delivery evidence against the specific order. The record may support more than one explanation.

Failure mode 1avoid
Treat every dispute as dishonest. That ignores service failures.
Failure mode 2avoid
Assume a status proves correct delivery. The destination still matters.
Failure mode 3avoid
Ignore repeated merchant complaints. They may reveal a systemic issue.
The record may support more than one explanation. The branches show why alternative designs fail. Chapter sources · Open image

Merchant behavior can create customer risk

A merchant can misstate products, hide recurring charges, use misleading descriptors, or process transactions for undisclosed businesses. Underwriting is therefore not a one-time identity check. Compare the operating business with the approved model and monitor material changes.

Use website evidence, complaint themes, fulfillment behavior, and transaction patterns together. Preserve dated observations because websites and terms change. A sudden shift in average ticket or geography may reflect a legitimate expansion, but it should fit the merchant’s explanation and authority. The control should test the mismatch, not punish growth itself.

Inside the mechanism. Merchant behavior can create risk through misleading offers, poor fulfillment, inaccessible support, or unstable refund practices. Connect customer complaints and disputes to product, campaign, and fulfillment cohorts. A payment model that looks only at payer credentials can miss this source of harm. Separate inability to deliver from deliberate deception unless evidence supports intent. Both may require action, but the investigation and recovery prospects differ.

A concrete example. A merchant can generate customer losses through failed fulfillment even without a false customer identity. Fast growth can increase the open promise faster than financial resources. The case has $565,000 of exposure. Its stated one-year PD and LGD imply $20,198.75 of expected loss, while the cover analysis leaves $441,000.00 of stress exposure. Monthly cash coverage is 0.93×. These are separate measures: one describes an average under probability assumptions, one describes available cover, and one describes a period’s funding capacity.

When the assumption fails. The platform approves growth using volume alone while deliveries deteriorate. Connect fulfillment quality, unfulfilled obligations, usable cover, and repayment capacity. The following worked sequence shows the reference condition, a stress condition, and a response condition with explicit synthetic data. These are comparative assumptions, not measured causal effects.

Follow a worked case3 conditions · 36 figures

A merchant can generate customer losses through failed fulfillment even without a false customer identity. Fast growth can increase the open promise faster than financial resources.

Merchant behavior can create customer risk — the flow
Merchant behavior can create customer risk Merchant behavior can create customer risk — the flow Follow the sequence. Test mismatches and customer harm. Approve Record the stated business model Observe Monitor material operating changes Review Test mismatches and customer harm
  1. ApproveRecord the stated business model
  2. ObserveMonitor material operating changes
  3. ReviewTest mismatches and customer harm
Follow the sequence. Test mismatches and customer harm. Chapter sources · Open image
Merchant behavior can create customer risk — the distinction
Merchant behavior can create customer risk Merchant behavior can create customer risk — the distinction These concepts answer different questions. Read each definition in the context of the section. Legitimate expansion Supported change in the business Undisclosed activity Processing differs from the approved model
Legitimate expansion
  • Supported change in the business
Undisclosed activity
  • Processing differs from the approved model
These concepts answer different questions. Read each definition in the context of the section. Chapter sources · Open image
Merchant change review
Merchant behavior can create customer risk Merchant change review Fictional teaching record. Tests the new offer. Merchant change review Illustrative data; not a real customer record or a prescribed policy. Approved product home goods Original model Current descriptor subscription service Changed behavior Evidence dated checkout capture Tests the new offer Identity alone does not establish ongoing conduct
Fictional educational excerpt / Not for execution

Merchant change review

Illustrative data; not a real customer record or a prescribed policy.

  1. Approved producthome goods

    Original model

  2. Current descriptorsubscription service

    Changed behavior

  3. Evidencedated checkout capture

    Tests the new offer

Identity alone does not establish ongoing conduct

Fictional teaching record. Tests the new offer. Chapter sources · Open image
Merchant behavior can create customer risk — control and failure modes
Merchant behavior can create customer risk Merchant behavior can create customer risk — control and failure modes Identity alone does not establish ongoing conduct. The branches show why alternative designs fail. Control design Compare live activity with the approved business. Identity alone does not establish ongoing conduct. Failure mode 1 Assume onboarding approval never expires. Businesses and risks change. avoid Failure mode 2 Treat all growth as fraud. Expansion can be legitimate. avoid Failure mode 3 Use an undated screenshot. It may not show the relevant customer experience. avoid
Control design

Compare live activity with the approved business. Identity alone does not establish ongoing conduct.

Failure mode 1avoid
Assume onboarding approval never expires. Businesses and risks change.
Failure mode 2avoid
Treat all growth as fraud. Expansion can be legitimate.
Failure mode 3avoid
Use an undated screenshot. It may not show the relevant customer experience.
Identity alone does not establish ongoing conduct. The branches show why alternative designs fail. Chapter sources · Open image

Refunds and promotions need state controls

A refund, credit, and promotional benefit each change an obligation or entitlement. Model their eligibility and consumption so retries do not issue value twice. Link a refund to the original payment and enforce the allowed cumulative amount.

Separate a commercial goodwill credit from a reversal of the original charge. Otherwise, support may believe a customer was refunded while finance sees an unrelated credit. Record who can authorize an exception and why. Review exception patterns for product defects as well as misuse. Many repeated credits begin with an unreliable service rather than an inventive customer.

A refund is a new financial action with a relationship to an earlier purchase. Its permitted value depends on prior captures, prior refunds, currency, and product policy. Two support agents can each see an apparently refundable order and submit overlapping actions. A correct interface does not solve that race by itself; the server must enforce the remaining refundable amount within an appropriate transaction boundary.

Promotions have similar state problems. Eligibility, redemption, cancellation, and restoration need explicit transitions. Otherwise, customers can encounter inconsistent treatment and repeated requests can create unintended value. Before classifying a pattern as deliberate abuse, establish that the product itself did not promise or repeatedly grant the benefit. The distinction changes both the control and the customer response.

Inside the mechanism. Refund and promotion limits need atomic state, not only a pre-check. Two workers can each observe remaining value and both consume it. Model requested, reserved, executed, failed, and released amounts with a stable operation key. Protect the invariant that total effective refunds do not exceed the permitted amount for that purchase, subject to explicitly modeled adjustments. A retry should reuse the same business operation rather than obtain a new allowance.

A concrete example. Value-changing actions can arrive through customer support, automated jobs, and provider events at the same time. The allowed remaining value is shared state. 145 intended requests generate 152 processing attempts under this retry assumption. Capacity is 180 attempts per interval, and the critical path consumes 150 ms of a 210 ms budget. The request-based SLO view observes 100 bad requests against an illustrative allowance of 100. These measurements must be connected to the financial effect and control evidence before declaring recovery.

When the assumption fails. Two requests each see the same refundable amount and both commit. Enforce the remaining amount atomically and make retries reuse one business action. The following worked sequence shows the reference condition, a stress condition, and a response condition with explicit synthetic data. These are comparative assumptions, not measured causal effects.

Follow a worked case3 conditions · 36 figures

Value-changing actions can arrive through customer support, automated jobs, and provider events at the same time. The allowed remaining value is shared state.

Refunds and promotions need state controls — the flow
Refunds and promotions need state controls Refunds and promotions need state controls — the flow Follow the sequence. Track cumulative refunds and credits. Eligibility Confirm the original obligation Issue Record the specific value movement Reconcile Track cumulative refunds and credits
  1. EligibilityConfirm the original obligation
  2. IssueRecord the specific value movement
  3. ReconcileTrack cumulative refunds and credits
Follow the sequence. Track cumulative refunds and credits. Chapter sources · Open image
Refunds and promotions need state controls — the distinction
Refunds and promotions need state controls Refunds and promotions need state controls — the distinction These concepts answer different questions. Read each definition in the context of the section. Refund Linked return of a payment amount Goodwill credit Separate commercial adjustment
Refund
  • Linked return of a payment amount
Goodwill credit
  • Separate commercial adjustment
These concepts answer different questions. Read each definition in the context of the section. Chapter sources · Open image
Refund limit specimen
Refunds and promotions need state controls Refund limit specimen Fictional teaching record. Simple available refund balance. Refund limit specimen Illustrative data; not a real customer record or a prescribed policy. Original captured 100 USD Maximum source amount before rules Already refunded 60 USD Linked prior refund Remaining 40 USD Simple available refund balance Repeated calls must not exceed the allowed amount
Fictional educational excerpt / Not for execution

Refund limit specimen

Illustrative data; not a real customer record or a prescribed policy.

  1. Original captured100 USD

    Maximum source amount before rules

  2. Already refunded60 USD

    Linked prior refund

  3. Remaining40 USD

    Simple available refund balance

Repeated calls must not exceed the allowed amount

Fictional teaching record. Simple available refund balance. Chapter sources · Open image
Refunds and promotions need state controls — control and failure modes
Refunds and promotions need state controls Refunds and promotions need state controls — control and failure modes Repeated calls must not exceed the allowed amount. The branches show why alternative designs fail. Control design Enforce cumulative linked refund limits. Repeated calls must not exceed the allowed amount. Failure mode 1 Reset the refund total on retry. That creates duplicate value. avoid Failure mode 2 Treat goodwill as a deleted sale. The accounting events differ. avoid Failure mode 3 Allow unlogged exceptions. The reason and authority must be traceable. avoid
Control design

Enforce cumulative linked refund limits. Repeated calls must not exceed the allowed amount.

Failure mode 1avoid
Reset the refund total on retry. That creates duplicate value.
Failure mode 2avoid
Treat goodwill as a deleted sale. The accounting events differ.
Failure mode 3avoid
Allow unlogged exceptions. The reason and authority must be traceable.
Repeated calls must not exceed the allowed amount. The branches show why alternative designs fail. Chapter sources · Open image

Keep labels revisable and traceable

A label should state its definition, evidence, source, confidence, and time. Confirmed unauthorized use, merchant non-delivery, unresolved dispute, and technical duplicate are different outcomes. Collapsing them into one bad flag teaches a model a confused objective.

Version labels when evidence changes. Preserve the prior label and the reason for correction. A model trained last month should be reproducible using the labels available then. Review agreement between analysts and sample unresolved cases. High agreement can still be wrong if everyone uses the same flawed instructions, so compare with independent evidence where possible.

Labels should retain their history. A dispute can begin as an allegation, become a confirmed delivery problem, and later close with a partial refund. Overwriting every stage with a final word such as fraud removes information needed to explain earlier decisions. Store the original event, the label source, confidence or review status, the effective time, and subsequent corrections. A model trained from these records needs a defined outcome at a defined observation date, not an accidental mixture of every intermediate operational status.

Inside the mechanism. A label is a versioned conclusion attached to evidence and a definition. Preserve original and revised outcomes with their effective and observation times. Training pipelines need a stated cutoff and a reproducible label version. Otherwise a historical evaluation can change silently as cases mature. Reviewer disagreement, overturned decisions, and incomplete outcomes should remain visible rather than being forced into a falsely precise binary label.

A concrete example. An allegation can become a delivery issue and later close with a partial recovery. Model data needs a defined outcome at a defined observation date. The case identifies 3,154 eligible records from a source population of 3,800. The required workflow completes for 3,059, but 46 completed records miss the illustrative internal target. Another 95 remain incomplete. Communication evidence covers 3,028 generated notices. Scope, completion, timeliness, and delivery are four separate properties of the customer outcome.

When the assumption fails. A final label overwrites earlier states and erases the basis of past decisions. Store label source, definition, effective time, confidence state, and correction history. The following worked sequence shows the reference condition, a stress condition, and a response condition with explicit synthetic data. These are comparative assumptions, not measured causal effects.

Follow a worked case3 conditions · 36 figures

An allegation can become a delivery issue and later close with a partial recovery. Model data needs a defined outcome at a defined observation date.

Keep labels revisable and traceable — the flow
Keep labels revisable and traceable Keep labels revisable and traceable — the flow Follow the sequence. Preserve the correction history. Define Use a specific outcome taxonomy Evidence Attach source and confidence Revise Preserve the correction history
  1. DefineUse a specific outcome taxonomy
  2. EvidenceAttach source and confidence
  3. RevisePreserve the correction history
Follow the sequence. Preserve the correction history. Chapter sources · Open image
Keep labels revisable and traceable — the distinction
Keep labels revisable and traceable Keep labels revisable and traceable — the distinction These concepts answer different questions. Read each definition in the context of the section. Current label Best present interpretation Historical label What was known at the earlier cutoff
Current label
  • Best present interpretation
Historical label
  • What was known at the earlier cutoff
These concepts answer different questions. Read each definition in the context of the section. Chapter sources · Open image
Label correction
Keep labels revisable and traceable Label correction Fictional teaching record. Documented basis. Label correction Illustrative data; not a real customer record or a prescribed policy. Version 1 unresolved dispute Initial evidence Version 2 merchant non-delivery Later fulfillment finding Reason carrier confirmed loss Documented basis Corrections should not erase the training history
Fictional educational excerpt / Not for execution

Label correction

Illustrative data; not a real customer record or a prescribed policy.

  1. Version 1unresolved dispute

    Initial evidence

  2. Version 2merchant non-delivery

    Later fulfillment finding

  3. Reasoncarrier confirmed loss

    Documented basis

Corrections should not erase the training history

Fictional teaching record. Documented basis. Chapter sources · Open image
Keep labels revisable and traceable — control and failure modes
Keep labels revisable and traceable Keep labels revisable and traceable — control and failure modes Corrections should not erase the training history. The branches show why alternative designs fail. Control design Version labels and their evidence. Corrections should not erase the training history. Failure mode 1 Overwrite every old label silently. Past results become irreproducible. avoid Failure mode 2 Use one bad flag for all outcomes. Different loss causes get mixed. avoid Failure mode 3 Treat analyst agreement as perfect truth. Shared instructions can create shared errors. avoid
Control design

Version labels and their evidence. Corrections should not erase the training history.

Failure mode 1avoid
Overwrite every old label silently. Past results become irreproducible.
Failure mode 2avoid
Use one bad flag for all outcomes. Different loss causes get mixed.
Failure mode 3avoid
Treat analyst agreement as perfect truth. Shared instructions can create shared errors.
Corrections should not erase the training history. The branches show why alternative designs fail. Chapter sources · Open image

Close the loop into product design

Some fraud-like losses disappear when the product becomes clearer. A recognizable descriptor reduces unrecognized-payment claims. Clear cancellation and refund states reduce repeat contacts. Reliable delivery records improve both customer service and dispute handling.

Rank recurring causes by customer harm, loss, and preventability. Assign product fixes alongside detection changes. Verify the result using comparable cohorts and a sufficiently mature outcome window. If a new rule blocks more customers but the underlying complaint remains, it may be hiding a product defect rather than solving it.

Inside the mechanism. A repeated loss pattern can expose a product design fault: a confusing cancellation flow, a weak refund state machine, or a missing delivery record. Aggregate supported mechanisms rather than merely counting bad customers. Assign the change to the team that owns the relevant behavior and verify the effect on the affected population. The feedback loop closes when the product behavior changes and the evidence shows that the specific failure is reduced.

A concrete example. A product can repeatedly grant value because its cancellation or restoration rules are unclear. Fixing the state model may reduce the incentive without adding friction to every customer. The comparison arm has 210/5000 adverse outcomes (4.20%) and the treatment arm has 193/5000 (3.86%). The absolute difference is -0.34 percentage points, with an illustrative large-sample 95% interval from -1.11 to 0.43. Interpretation depends on assignment integrity, outcome maturity, independence, and the actual decision being evaluated.

When the assumption fails. A control rollout is judged only by a lower refund count. Measure the defined loss path, legitimate refunds, support load, and customer completion under a valid comparison. The following worked sequence shows the reference condition, a stress condition, and a response condition with explicit synthetic data. These are comparative assumptions, not measured causal effects.

Follow a worked case3 conditions · 36 figures

A product can repeatedly grant value because its cancellation or restoration rules are unclear. Fixing the state model may reduce the incentive without adding friction to every customer.

Close the loop into product design — the flow
Close the loop into product design Close the loop into product design — the flow Follow the sequence. Measure mature comparable outcomes. Find cause Link complaints to workflow failures Change product Repair the confusing step Verify Measure mature comparable outcomes
  1. Find causeLink complaints to workflow failures
  2. Change productRepair the confusing step
  3. VerifyMeasure mature comparable outcomes
Follow the sequence. Measure mature comparable outcomes. Chapter sources · Open image
Close the loop into product design — the distinction
Close the loop into product design Close the loop into product design — the distinction These concepts answer different questions. Read each definition in the context of the section. Detection patch Finds more symptoms Product repair Removes a recurring cause
Detection patch
  • Finds more symptoms
Product repair
  • Removes a recurring cause
These concepts answer different questions. Read each definition in the context of the section. Chapter sources · Open image
Descriptor improvement
Close the loop into product design Descriptor improvement Fictional teaching record. Compare mature cohorts. Descriptor improvement Illustrative data; not a real customer record or a prescribed policy. Old wording unfamiliar processor name Recognition problem New wording clear merchant name Customer context Measure unrecognized claims Compare mature cohorts Prevention can improve the product itself
Fictional educational excerpt / Not for execution

Descriptor improvement

Illustrative data; not a real customer record or a prescribed policy.

  1. Old wordingunfamiliar processor name

    Recognition problem

  2. New wordingclear merchant name

    Customer context

  3. Measureunrecognized claims

    Compare mature cohorts

Prevention can improve the product itself

Fictional teaching record. Compare mature cohorts. Chapter sources · Open image
Close the loop into product design — control and failure modes
Close the loop into product design Close the loop into product design — control and failure modes Prevention can improve the product itself. The branches show why alternative designs fail. Control design Fix recurring service and clarity defects. Prevention can improve the product itself. Failure mode 1 Only tighten decline rules. That may hide the cause. avoid Failure mode 2 Compare yesterday with mature old cohorts. Outcome age differs. avoid Failure mode 3 Count fewer complaints without volume context. Traffic changes can explain the count. avoid
Control design

Fix recurring service and clarity defects. Prevention can improve the product itself.

Failure mode 1avoid
Only tighten decline rules. That may hide the cause.
Failure mode 2avoid
Compare yesterday with mature old cohorts. Outcome age differs.
Failure mode 3avoid
Count fewer complaints without volume context. Traffic changes can explain the count.
Prevention can improve the product itself. The branches show why alternative designs fail. Chapter sources · Open image

Chapter connections

This chapter builds on Scams, money mules, and social engineering. Use the glossary for terminology and risk mathematics for formulas and worked calculations.

Sources

Reviewed 2026-09-17
  1. Stripe: how disputes work (provider example)
  2. Stripe: PaymentIntent lifecycle (provider example)