Score API: Reputation Based Scoring

Delivers reputation scoring based on phone number intelligence, traffic patterns, machine learning, and a global data consortium

Get started

Assess fraud risk with phone number intelligence & machine learning

At an alarming rate, bad actors create online and mobile application accounts that result in spam, phishing attacks, promo abuse, and other costly fraud. By registering fake accounts, fraudsters can attack legitimate users and damage a brand’s value, revenue, and growth. Effectively identifying and blocking these harmful users at account registration, while streamlining the process for authentic and valuable users, has become critical.


Grow User Base Responsibly

Streamline the account registration process, increase conversions and securely grow ecosystem of verified and valuable users.

Identify Fake & Suspicious Users

Mitigate more fraudulent activity and validate that end-users are who they say they are.

Protect Brand Reputation And Value

Reduce the negative impacts of fraud while creating a more authentic and valuable user base.

Get started

"We measured the impact by several factors: The number of abuse reports from Skype Number owners and the amount of abuse reports dropped since we started to use Score. We used the assumption that robocalls do not last long, so if number of robocalls decreased our ACD (Average Call Duration) should grow. We also tracked social networks and media for any negative PR in regards to robocalls."

Anton Volkov

Program Manager

How We Score

Phone Number Data & Analytics

Phone number data attributes including phone type, telecom carrier, account and device ID and IP address are evaluated to identify potential fraud risk.

Global Fraud Data Consortium

Score leverages two global databases to help detect and identify known fraud faster. TeleBureauTM, TeleSign’s database of customer-contributed phone number reputation information & BICS Global Telco Fraud Data, a crowdsourced telco incidents database of suspicious network activity.

Traffic Pattern Recognition & Usage Velocity

Anomalous traffic behavior patterns and usage velocity may raise red flags. For example, if passcode requests are received in five different languages from the same number in the same week or a range of numbers are seen repeatedly on one or more Web services, it may be a sign that a phone is being shared, and the risk score will increase accordingly.

Machine Learning

A data analysis technique that trains an algorithm to uncover hidden insights in data to predict fraudulent or high risk phone numbers. Customized machine learning models using customer-provided data further increase the effectiveness and accuracy of Score’s fraud detection capabilities.

Evaluation Of Customer-Provided Data Inputs

Score’s machine learning model can also evaluate unique customer-provided data inputs such as user IP address, email address, account ID, and device ID with each API request to further increase the effectiveness of risk assessments, specific to the customer’s environment.

Actionable Risk Assessment Recommendation

A data-driven risk assessment score is delivered that helps determine the appropriate action of whether to allow, block, or flag a registration or transaction. Score can be used as a standalone solution, easily integrated with other solutions or combined with SMS to challenge users when flagged.

Talk To An Expert

Interested in learning about how TeleSign's identity and engagement solutions can prevent fraud while fostering secure and global growth for your business? Let's chat.