Sift Intellectual Property

Patents

Sift’s services leverage the features and functionality of different patents owned by Sift Science, Inc. as listed below. For more information about our services, please see our Terms of Service and our Digital Trust & Safety product suite.

Patent Number Grant Date Description
9,954,87904/24/2018 Workflow platform that allows customer teams to build and update their fraud processes without needing to write code; enables set up of workflows that automate any type of fraud detection achievable on Sift's platform.
10,284,58205/07/2019
10,643,21605/05/2020
9,978,06705/22/2018Enables the classification of multiple types of fraud and abuse simultaneously on a single account via the use of global and custom models, and ensemble of models. A distinct fraud score can be computed for each listed type of fraud.
10,108,96210/23/2018
10,296,91205/21/2019
10,402,82809/03/2019
10,181,03201/15/2019Enables the detection of account misappropriation and produces a risk score that indicates when an account may be being used by someone other than the original creator.
10,482,39511/19/2019
10,339,47207/02/2019 Enables migration from an old risk scoring model to a new risk scoring model for a given customer to address changes and trends in fraud patterns. The calibration keeps score distributions stable even when Sift migrates customers between model types.
10,572,83202/25/2020
10,341,37407/02/2019Provides an analytical framework for evaluating anomalous shifts in risk scores for a given customer, allowing Sift to validate a new scoring model for a given customer before deployment and blocks deployment until validated.
10,462,17210/29/2019
10,623,42304/14/2020 Prevents interferences between customer analysts reviewing a transaction within the Sift platform, providing real time updates to systems and client browsers interacting with the review queue.
10,491,61711/26/2019Varies the weights on a per customer basis of the models that make up Sift’s global scoring model to generate more accurate and specific risk scores.
10,666,67405/26/2020
11,070,58507/20/2021Produces a prediction that includes a risk score for posted content, and may include multiple distinct models that operate together as a unified risk model to predict whether abuse or fraudulent content is likely to occur.
11,303,66504/12/2022
10,929,75602/23/2021 Provides a proxy model for interpreting complex black box models by constructing a surrogate model that mimics outputs of a black box model.
10,897,47901/19/2021 Provides automatic multi-factor authentication to Sift's service, enabling both direct verification requests and verification requests triggered by an automated workflow. Verification data may be used as training data to improve customer-specific models.
10,958,67303/23/2021
10,997,60805/04/2021Enables a customer to Sift's service to determine false positive rates in declines or adverse decisions output from automated workflows.
11,068,91007/20/2021
11,037,17306/15/2021Allows for automated anomaly detection in decisions output from automated workflows.
11,049,11606/29/2021
11,330,00905/10/2022Implements text clustering models and techniques to surface fraudulent or abusive patterns in online content across users.
11,528,29012/13/2022
11,429,97408/30/2022Selectively identifies salient signals for card testing and converts those signals into learnable features that may be added to an existing machine learning.
Allowed; second patent pending
11,409,62908/09/2022Enables robust testing of workflow routes for identifying optimal routes for improving automated proposals for digital handling.
Allowed; second patent pending
11,496,50111/8/2022 Enables bulk labeling of corpora of data samples using a variety of techniques for exploring and identifying groups or networks of fraudulent and legitimate data samples.
Allowed; second patent pending
Allowed; patent pending Introduces an active learning-informed data sampling technique for creating a labeled corpus of samples for effectively training a model.
Allowed; patent pending Provides several mechanisms for automatically creating workflows and workflow routes for new and existing Sift customers.
Patent pendingCreates and enables an automated agent for accelerating chargeback disputes by automatically scoring the success of a chargeback based on known transaction evidence and proposing transaction evidence that may improve the probability of success.
Patent pending Enables customers and partners to integrate with and interchange data through Sift's systems by an extensible webhook service.
Patent allowed Identifies anomalies in risk score distributions including shifts or drifts to generate an explanation for the anomalous behavior(s) together with corrective actions taken to mitigate the anomalies.
Allowed; patent pending Identifies fraudulent automated bot activities and generates a unique bot signature for each distinct bot that is detected and which can be leveraged in real-time bot identification to accelerate detection and threat mitigation posed by malicious bots.
Patent Number Grant Date
9,954,87904/24/2018
10,284,58205/07/2019
10,643,21605/05/2020
Description
Workflow platform that allows customer teams to build and update their fraud processes without needing to write code; enables set up of workflows that automate any type of fraud detection achievable on Sift's platform.
Patent Number Grant Date
9,978,06705/22/2018
10,108,96210/23/2018
10,296,91205/21/2019
10,402,82809/03/2019
Description
Enables the classification of multiple types of fraud and abuse simultaneously on a single account via the use of global and custom models, and ensemble of models. A distinct fraud score can be computed for each listed type of fraud.
Patent Number Grant Date
10,181,03201/15/2019
10,482,39511/19/2019
Description
Enables the detection of account misappropriation and produces a risk score that indicates when an account may be being used by someone other than the original creator.
Patent Number Grant Date
10,339,47207/02/2019
10,572,83202/25/2020
Description
Enables migration from an old risk scoring model to a new risk scoring model for a given customer to address changes and trends in fraud patterns. The calibration keeps score distributions stable even when Sift migrates customers between model types.
Patent Number Grant Date
10,341,37407/02/2019
10,462,17210/29/2019
Description
Provides an analytical framework for evaluating anomalous shifts in risk scores for a given customer, allowing Sift to validate a new scoring model for a given customer before deployment and blocks deployment until validated.
Patent Number Grant Date
10,623,42304/14/2020
Description
Prevents interferences between customer analysts reviewing a transaction within the Sift platform, providing real time updates to systems and client browsers interacting with the review queue.
Patent Number Grant Date
10,491,61711/26/2019
10,666,67405/26/2020
Description
Varies the weights on a per customer basis of the models that make up Sift’s global scoring model to generate more accurate and specific risk scores.
Patent Number Grant Date
11,070,58507/20/2021
11,303,66504/12/2022
Description
Produces a prediction that includes a risk score for posted content, and may include multiple distinct models that operate together as a unified risk model to predict whether abuse or fraudulent content is likely to occur.
Patent Number Grant Date
10,929,75602/23/2021
Description
Provides a proxy model for interpreting complex black box models by constructing a surrogate model that mimics outputs of a black box model.
Patent Number Grant Date
10,897,47901/19/2021
10,958,67303/23/2021
Description
Provides automatic multi-factor authentication to Sift's service, enabling both direct verification requests and verification requests triggered by an automated workflow. Verification data may be used as training data to improve customer-specific models.
Patent Number Grant Date
10,997,60805/04/2021
11,068,91007/20/2021
Description
Enables a customer to Sift's service to determine false positive rates in declines or adverse decisions output from automated workflows.
Patent Number Grant Date
11,037,17306/15/2021
11,049,11606/29/2021
Description
Allows for automated anomaly detection in decisions output from automated workflows.
Patent Number Grant Date
11,330,00905/10/2022
11,528,29012/13/2022
Description
Implements text clustering models and techniques to surface fraudulent or abusive patterns in online content across users.
Patent Number Grant Date
11,429,97408/30/2022
Allowed; second patent pending
Description
Selectively identifies salient signals for card testing and converts those signals into learnable features that may be added to an existing machine learning.
Patent Number Grant Date
11,409,62908/09/2022
Allowed; second patent pending
Description
Enables robust testing of workflow routes for identifying optimal routes for improving automated proposals for digital handling.
Patent Number Grant Date
11,496,50111/8/2022
Allowed; second patent pending
Description
Enables bulk labeling of corpora of data samples using a variety of techniques for exploring and identifying groups or networks of fraudulent and legitimate data samples.
Patent Number Grant Date
Allowed; patent pending
Description
Introduces an active learning-informed data sampling technique for creating a labeled corpus of samples for effectively training a model.
Patent Number Grant Date
Allowed; patent pending
Description
Provides several mechanisms for automatically creating workflows and workflow routes for new and existing Sift customers.
Patent Number Grant Date
Patent pending
Description
Creates and enables an automated agent for accelerating chargeback disputes by automatically scoring the success of a chargeback based on known transaction evidence and proposing transaction evidence that may improve the probability of success.
Patent Number Grant Date
Patent pending
Description
Enables customers and partners to integrate with and interchange data through Sift's systems by an extensible webhook service.
Patent Number Grant Date
Patent allowed
Description
Identifies anomalies in risk score distributions including shifts or drifts to generate an explanation for the anomalous behavior(s) together with corrective actions taken to mitigate the anomalies.
Patent Number Grant Date
Allowed; patent pending
Identifies fraudulent automated bot activities and generates a unique bot signature for each distinct bot that is detected and which can be leveraged in real-time bot identification to accelerate detection and threat mitigation posed by malicious bots.

Trademarks

Sift Science Inc. (“Sift”) uses the terms and/or logos (“Sift Trademarks”) below as active trademarks in branding its products and services. The Sift brand is an important symbol of our mission to help everyone trust the Internet. We have registered or applied for registration of these trademarks in the United States and other countries around the world.

Word Mark: Sift

Sift wordmark

Logos

Any use of Sift Trademarks requires prior written authorization of Sift. Sift has the sole right to prevent, revoke consent, or terminate the use of its trademarks by any licensee or other permitted user. All Sift Trademarks are, and shall remain, the exclusive property of Sift, and authorized use by third parties will accrue to the benefit of Sift. Sift monitors the use of its trademarks and reserves the right to request that third parties modify or terminate any use that violates these guidelines, creates a likelihood of confusion, or dilutes Sift Trademarks.