# Risikobewertung Greifen Sie auf die Risikobewertungen von Stripe Radar im Dashboard und über die API zu. Während Stripe Radar Sie bei der Überwachung Ihrer Zahlungen und dem Schutz Ihres Unternehmens vor Zahlungsanfechtungen unterstützt, sind Sie [letztendlich verantwortlich](https://stripe.com/us/legal#processing-transactions-disputes) für alle Zahlungen, die Sie annehmen. Dazu zählen auch Zahlungen, die im späteren Verlauf angefochten werden oder sich als Betrug erweisen. Stripe Radar includes an adaptive [AI model](https://stripe.com/radar/guide) that uses a risk score to evaluate the risk level for each payment in real time. The model uses hundreds of signals about each payment and data across our network of businesses to predict whether a payment is likely to be fraudulent. It learns from new customer purchase patterns and transaction features, and incorporates feedback from you whenever payments are marked as fraudulent. Risk settings and the risk controls for fraudulent disputes and early fraud warnings don’t use this AI model. They use more specialized models that can balance the tradeoffs between authorization and fraud. > Wenn ein Unternehmen, das Stripe nutzt, eine Karte, ein SEPA-Lastschriftkonto oder ein ACH-Konto erkennt, hat Stripe wahrscheinlich in der Vergangenheit Zahlungen für diese Zahlungsmethode verarbeitet: > > - Chance von 92 %, dass wir die Karte schon einmal gesehen haben - Chance von 82 %, dass wir das SEPA-Konto schon einmal gesehen haben - Chance von 71 %, dass wir das ACH-Konto schon einmal gesehen haben ## Wann wird Radar verwendet? Radar evaluates risk and runs rules for three Stripe API objects: [Charges](https://docs.stripe.com/api/charges.md), [PaymentIntents](https://docs.stripe.com/api/payment_intents.md) and [SetupIntents](https://docs.stripe.com/api/setup_intents.md). Stripe designed the Radar rules to take four actions: - 3DS-Authentifizierung anfordern - Erstellung des Objekts zulassen - Erstellung des Objekts blockieren - Review the creation of a charge In der folgenden Tabelle wird veranschaulicht, welche Regeln Radar für jede Art von API-Objekt ausführt: | Transaktionstyp | 3DS anfordern | Allow and Block | Überprüfen | | --------------- | ------------------- | --------------- | ------------------- | | Charge | - Nicht unterstützt | ✓ Supported | ✓ Supported | | PaymentIntent | ✓ Supported | ✓ Supported | ✓ Supported | | SetupIntent | ✓ Supported | ✓ Supported | - Nicht unterstützt | If you use card payments, you can enable Radar for SetupIntents in your [Radar settings](https://dashboard.stripe.com/test/radar/settings). ### Use Radar with Stripe Checkout or Stripe Billing This information also applies to payments created using Stripe Checkout and Stripe Billing. To provide a seamless flow for your *subscription* (A Subscription represents the product details associated with the plan that your customer subscribes to. Allows you to charge the customer on a recurring basis) customers, the Radar fraud models only score the initial payment of a recurring Stripe Billing subscription, but evaluate rules for all payments. ## Risikoergebnisse With Stripe Radar for Fraud Teams, each payment also includes a risk score that ranges from 0–99 to indicate the risk level on a more granular level. By default, a score of 65 or above indicates elevated risk, while a score of 75 or above indicates high risk. The Stripe AI model evaluates the likelihood that a payment is fraudulent, and provides an assessment of one of the following values: - [Hohes Risiko](https://docs.stripe.com/radar/risk-evaluation.md#high-risk) - [Erhöhtes Risiko](https://docs.stripe.com/radar/risk-evaluation.md#elevated-risk) - [Normales Risiko](https://docs.stripe.com/radar/risk-evaluation.md#normal-risk) - [Nicht bewertet](https://docs.stripe.com/radar/risk-evaluation.md#not-evaluated) - [Unbekanntes Risiko](https://docs.stripe.com/radar/risk-evaluation.md#unknown-risk) Jede Zahlung beinhaltet Informationen zum *Ergebnis* unserer Risikobewertung. Radar for Fraud Teams lets you see a [risk insights](https://docs.stripe.com/radar/reviews/risk-insights.md) section on the payment page that provides more details about why we assigned a payment a particular risk level and score. If a financial institution (such as a card issuer or bank) [declines](https://docs.stripe.com/declines.md) a payment, Stripe also includes any information we receive from them as part of the outcome. You can see the outcome for each payment in the [Dashboard](https://dashboard.stripe.com/), or through the API in the [Outcome](https://docs.stripe.com/api.md#charge_object-outcome) attribute of the [Charge](https://docs.stripe.com/api.md#charge_object) object. ### Zahlungen mit hohem Risiko Stripe kennzeichnet Zahlungen als hochriskant, wenn sie nach unserer Einschätzung wahrscheinlich betrügerisch sind. Zahlungen mit dieser Risikostufe werden standardmäßig [blockiert](https://docs.stripe.com/radar/rules.md#built-in-rules). Für das Objekt `Charge` einer Zahlung mit hohem Risiko ist `risk_level` auf `highest` festgelegt. ```json ... "outcome": { "network_status": "not_sent_to_network", "reason": "highest_risk_level", "risk_level": "highest", "risk_score": 92, // Provided only with Stripe Radar for Fraud Teams "seller_message": "Stripe blocked this charge as too risky.", "type": "blocked", } ... ``` If Stripe Radar blocks a payment that you know is legitimate, you can remove the block by viewing the payment in the Dashboard and clicking **Add to allow list**. Adding a payment to the allow list doesn’t retry the payment, but it does prevent Stripe Radar from blocking future payment attempts with that payment method or email address. > If you don’t see **Add to allow list**, you can [contact us](https://support.stripe.com/email) to add this feature to your Radar account. ### Zahlungen mit erhöhtem Risiko Elevated risk payments have an increased chance of being fraudulent. Stripe Radar allows payments of this risk level by default. Stripe Radar for Fraud Teams automatically places elevated risk payments into your [review](https://docs.stripe.com/radar/reviews.md) queue so you can look at them more closely. Für das Objekt `Charge` einer Zahlung mit erhöhtem Risiko ist `risk_level` auf `elevated` festgelegt. ```json ... "outcome": { "network_status": "approved_by_network", "reason": "elevated_risk_level", "risk_level": "elevated", "risk_score": 56, // Provided only with Stripe Radar for Fraud Teams "seller_message": "Stripe evaluated this charge as having elevated risk, and placed it in your manual review queue.", "type": "manual_review" } ... ``` ### Zahlungen mit normalem Risiko Payments with a normal risk evaluation have fewer characteristics that indicate fraud than payments with elevated or high risk levels. However, we recommend that you continue to be vigilant when fulfilling these orders. Payments that have normal risk can still turn out to be fraudulent, and there are other possible [types of fraud](https://docs.stripe.com/disputes/prevention/identifying-fraud.md) that can occur later in the order process. Für das Objekt `Charge` einer erfolgreich abgewickelten Zahlung mit normalem Risiko ist `risk_level` auf `normal` festgelegt. ```json ... "outcome": { "network_status": "approved_by_network", "reason": null, "seller_message": "The charge was authorized.", "risk_level": "normal", "risk_score": 23, // Provided only with Stripe Radar for Fraud Teams "type": "authorized", } ... ``` ### Nicht bewertet Radar assesses the risk level for card, ACH, and SEPA Direct Debit payments, and sets the risk level to `not_assessed` for: - All other non-card payments - Card-based payments predating the public assignment of risk levels - Payments where the business opts out of Radar fraud risk assessment Für das Objekt `Charge` einer Zahlung mit unbewertetem Risiko ist `risk_level` auf `not_assessed` festgelegt. ```json ... "outcome": { "network_status": "approved_by_network", "reason": "not_assessed_risk_level", "risk_level": "not_assessed", "seller_message": "Your business has opted out of Radar fraud risk assessments.", "type": "authorized" } ... ``` ### Zahlungen mit unbekanntem Risiko In unusual cases, an error might cause risk evaluation to fail. If this happens, Stripe reports the payment as having unknown risk. Für das Objekt `Charge` einer Zahlung mit unbekanntem Risiko ist `risk_level` auf `unknown` festgelegt. ```json ... "outcome": { "network_status": "approved_by_network", "reason": "unknown_risk_level", "risk_level": "unknown", "seller_message": "Something went wrong while evaluating this payment. Our engineers have been notified and we’ll look into this as soon as possible.", "type": "authorized" } ... ``` ## Search for a specific risk level in the Dashboard You can search for payments with a specific risk level using the **risk\_level** search term and the desired risk level. For example, a search for [risk_level:highest](https://dashboard.stripe.com/test/search?query=risk_level%3Ahighest) returns a list of all payments with a high risk level. A search for [risk_level:elevated](https://dashboard.stripe.com/test/search?query=risk_level%3Aelevated) returns a list of all payments with an elevated risk level. ## Provide feedback on risk evaluations While we use information across our network to evaluate a payment, you might have additional information about a payment as a result of a customer interaction. Our AI model responds to feedback you share with us, and you can help improve our fraud detection algorithms and the accuracy of our risk evaluations by [refunding](https://docs.stripe.com/refunds.md) and reporting payments that you believe are fraudulent. To refund a payment and mark it as fraudulent, do the following: 1. View the payment in the Dashboard. 1. Klicken Sie auf **Rückerstattung**. 1. Wählen Sie als **Grund** **Betrug** aus. 1. Geben Sie eine kurze Erklärung. Sie können eine Zahlung außerdem beim [Erstellen einer Rückerstattung](https://docs.stripe.com/api.md#create_refund) über die API als betrügerisch kennzeichnen, indem Sie für `reason` als Wert `fraudulent` angeben. Dadurch werden die mit der Zahlung verknüpfte E-Mail-Adresse und der Fingerabdruck der Karte den Standard-[Blocklisten](https://docs.stripe.com/radar/lists.md#default-lists) für E-Mail-Adressen und Kartenfingerabdrücke hinzugefügt. #### Ruby ```ruby # Don't put any keys in code. See https://docs.stripe.com/keys-best-practices. # Find your keys at https://dashboard.stripe.com/apikeys. Stripe.api_key = '<>' # If you haven't refunded the charge, you can do so and let Stripe # know it was fraudulent in one step. Stripe::Refund.create({ charge: '{{CHARGE_ID}}', reason: 'fraudulent', }) # If you already refunded the charge (without specifying the # 'fraudulent' reason), you can still let us know it was fraudulent. Stripe::Charge.update( '{{CHARGE_ID}}', { fraud_details: { user_report: 'fraudulent', }, } ) ``` For a small subset of payments, Stripe modifies the reported risk score so we can measure the performance of our models and obtain data for subsequent model development. This allows us to make sure key metrics, such as false positive rate and recall, remain within desirable ranges, and that model performance continues to improve. You can opt out of using the Stripe Radar API model by [contacting support](https://stripe.com/contact).