NS8 User Guides

Our score

NS8 developed a score to give users a simplified view of a complex problem: understanding website traffic. Our scoring engine inspects and scores everything that passes through it, returning a number between 0 and 1000.

Our score assesses the quality of advertising traffic as well as the risk of fraud for a transaction. Every user that visits your store and every action a user takes is scored by our scoring engine. Negative attributes such as a deceptive session, where the user is discovered to be lying about their device or location, will push their score down. Positive attributes, such as natural mouse movements, will push their score up.

The scale below demonstrates the ranges of score categories.

0 through 375 (Very Bad - Bad)

NS8 identified a bot session or detected a blatant attempt at deception. A high number of deceptive flags during a session will result in a lower score.

376 through 624 (Neutral)

A neutral score can mean that a mix of good and bad attributes was discovered, or in rare cases, that no attributes were discovered at all. Scores in this range may encompass valid human users who exhibit some suspicious behaviors.

625 through 1000 (Good - Excellent)

NS8 identified enough positive attributes to determine that there is a real human behind the session. Scores closer to 1000 are indicative of users who exhibit little to no suspicious behavior.

Scoring Attributes

Our scoring engine is powered by dynamic global data sets and machine learning to update its methodology as fraud techniques evolve. Scores are compiled by tracking over 170 unique attributes, beginning from the moment a visitor enters your website until the time they leave. In fact, some pre-session data (like referrers, campaign attributes, and cookies) is factored into a user's score. These attributes are all combined to determine a user's level of suspicion.

Scoring attributes are broken down into two main categories: user behavior and technology profiles.

User behavior attributes determine if a user is behaving like a human or a bot. Relevant attributes include navigation speed, mouse movement, session visibility, and some other patent-pending technologies.

Technology profile attributes reveal whether users are using tactics to mask their identity and location or are otherwise acting deceptively. Relevant attributes include browser profiles, IP address data, and other propriety methods.

Scoring is quite a complicated process behind the scenes—luckily, NS8 simplifies your life by providing the easy-to-understand score and supporting data. This supporting data is summarized in attributes like primary user issues and payment issues.

Updated about a month ago

Our score

Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.