See Sift in Action
Patent NumberGrant DateDescription
9,954,87904/24/2018Workflow 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.
10,284,58205/07/2019Workflow 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.
10,643,21605/05/2020Workflow 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.
9,978,06705/22/2018 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.
10,108,962 10/23/2018Enables 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.
10,296,912 05/21/2019Enables 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.
10,402,828 09/03/2019Enables 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.
10,181,032 01/15/2019 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.
10,482,395 11/19/2019Enables 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.
10,339,472 07/02/2019 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.
10,572,832 02/25/2020Enables 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.
10,341,374 07/02/2019 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.
10,462,172 10/29/2019Provides 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.
10,623,423 04/14/2020 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.
10,491,617 11/26/2019 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.
10,666,674 05/26/2020Varies 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.
11,070,585 07/20/2021 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.
11,303,665 04/12/2022Produces 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.
10,929,756 02/23/2021 Provides a proxy model for interpreting complex black box models by constructing a surrogate model that mimics outputs of a black box model.
10,897,479 01/19/2021 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.
10,958,673 03/23/2021Provides 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.
10,997,608 05/04/2021 Enables a customer to Sift's service to determine false positive rates in declines or adverse decisions output from automated workflows.
11,068,910 07/20/2021Enables a customer to Sift's service to determine false positive rates in declines or adverse decisions output from automated workflows.
11,037,173 06/15/2021 Allows for automated anomaly detection in decisions output from automated workflows.
11,049,116 06/29/2021Allows for automated anomaly detection in decisions output from automated workflows.
11,330,009 05/10/2022 Implements text clustering models and techniques to surface fraudulent or abusive patterns in online content across users.
11,528,290 12/13/2022Implements text clustering models and techniques to surface fraudulent or abusive patterns in online content across users.
11,429,974 08/30/2022 Selectively identifies salient signals for card testing and converts those signals into learnable features that may be added to an existing machine learning.
11,620,653 04/04/2023Selectively identifies salient signals for card testing and converts those signals into learnable features that may be added to an existing machine learning.
11,409,629 08/09/2022 Enables robust testing of workflow routes for identifying optimal routes for improving automated proposals for digital handling.
11,573,883 02/07/2023Enables robust testing of workflow routes for identifying optimal routes for improving automated proposals for digital handling.
11,496,501 11/08/2022 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.
11,645,386 05/09/2023Enables 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.
11,575,695 02/07/2023 Enables the creation of a connected component graph or network for exposing potential large scale attacks, such as bot attacks.
11,496,501 01/08/2022 Introduces an active learning-informed data sampling technique for creating a labeled corpus of samples for effectively training a model.
11,887,1263/17/2023Provides several mechanisms for automatically creating workflows and workflow routes for new and existing Sift customers.
11,916,92711/07/2022; Second 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.
11,720,66808/08/2023Identifies 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.
11,841,941 06/16/2023 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.
11,777,962 10/03/2023Identifies 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.
PendingIdentifies 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.
Pending Allows customers to evaluate and respond to events based on multiple scoring criteria by introducing a technique that assigns both an event score and one or more percentile scores to each evaluated event, and enables customers to design related workflows. This invention involves using a T-Digest algorithm for calibration.