The UK company claims by looking at variables such as where the streaming service is being used, the content watched, the device used to watch it and more it can calculate a probability of how likely it is a particular user is sharing their password. That might be an outright ban on the account or just a sternly-worded email telling them to pay for a premium account.
According to the firm, if the AI finds the sharing pattern extreme, for example the credentials being sold online to multiple users, it would be able to shut down such accounts.
Synamedia presented the technology at the CES 2019 conference in Las Vegas.
Jean Marc Racine, CPO of Synamedia, said: "Casual credentials sharing is becoming too expensive to ignore". A study from Parks Associates concluded that, by 2021, credentials sharing could account for $9.9 billion in losses for pay-TV revenues and $1.2 billion in OTT revenues. Many casual users will be happy to pay an additional fee for a premium, shared service with a greater number of concurrent users.
Research quoted by Synamedia reported that younger generations are used to accessing streaming services for free and rarely become paying customers.
It uses behavioral analytics and machine learning to track how many people are logged into a single account, as well as where they log in from.
"It's a great way to keep honest people honest while benefiting from an incremental revenue stream".
If an account is signed in and watching shows in both Edinburgh and London, Synamedia flags the user.
"For example, the solution can determine whether users are viewing at their main home and a holiday home, or whether they have shared credentials with friends or grown-up children who live away from home".
Synamedia says its system is being trialed now by a number of content providers, although it won't say exactly who they are.