Kontxt inspects the messages passing through an operator’s network. Its machine learning algorithms then look for patterns in the data in order to classify messages into clusters.

It can tell, for example, whether the messages are P2P or A2P, and it can differentiate delivery messages from promotional alerts and two-factor authentication codes.

Just as important, Kontxt can analyse the metadata to draw conclusions about the sender. And it can scrutinise the spelling of words that might indicate spam.

This AI-led approach to understanding mobile messaging traffic offers an alternative to the traditional method, which relies on firewalls.

And its ability to classify messages could present further opportunities. As well as being a defence against fraud and spam, it might also help operators to make their systems more efficient. How? By letting them prioritise urgent comms while scheduling less urgent alerts for when the network is quieter.

MEF is leading the charge against fraud and spam in messaging. To explore the potential of AI to tackle the problem, we scheduled a webinar titled: “The role of machine learning in enterprise communications.”

We’re creating so much data. As messaging gets so complicated we need another way of analysing the data to make some sense of it. NLP (neuro linguistic programming) lets you understand it and see trends and relationships in it.”

The two speakers were:

• Surash Patel, General Manager Messaging and VP, RealNetworks
• Chris Galdun, VP of Messaging Solutions, Syniverse

Here are the main talking points – You can see the full slide deck from the webinar here.

Filters and firewalls are ‘reactive’ forms of defence

“From a technological perspective, there’s been a lot of work around filters and firewalls,” says Surash Patel. “They look at the communications layer, at the IP address, and then analyse messages from that perspective. What we find is that these things are quite reactive. They spot things after they have happened and reprogram accordingly.”

Chris Galdun adds: “I agree it’s very static. Filters look for the IP address and for keywords after the fact and then block them. And what we find is that this is very limited because fraudsters make changes too. They will change the content of the message and the sender ID.”

Natural language processing offers a new way to analyse vast data sets

“We’re creating so much data,” says Patel. “As messaging gets so complicated we need another way of analysing the data to make some sense of it. NLP (neuro linguistic programming) lets you understand it and see trends and relationships in it.”

“Take the example of banking notifications. They all cluster together. So a customer can look at the route these messages have taken and say ‘OK these are the legitimate senders, and these are the ones I don’t recognise or don’t think are coming from those sources’. The system is very good at solving those problems quickly.”

Galdun agrees. “Historically, on our platform we looked for spam. But spam hard to define,” he says. “Is it true spam or just unwanted messaging? In the traditional model, this was black or white. Now, we can set up the rules differently. We can tune these rules as granularly as need be.”

But an AI system is only as good as its data set

“You look for generalisations in the data,” says Patel. “But you have to start with unbiased data. If your data is skewed, it will come to a particular conclusion. In machine learning, there’s a trade-off between ‘recall’ (how many correct interventions a system makes) and ‘precision’ (how few incorrect interventions it makes).

”We always have to balance recall with precision. We have to ask: are there instances we haven’t seen before, and did we detect them? Different industries have different priorities. We’re looking at both. We tune the model to what a particular customer needs.”

In the messaging space, an AI system can inspect traffic at the character level

“We look for messages that are very similar, and then try to understand what type of traffic it is,” says Patel. “Is it a two factor authentication? Is it a delivery alert or an appointment reminder?  We have human labellers that help with this.

“But the training doesn’t stop there. We can also look at the characters within the words. For example, does it say win or w1n? Then we look at the words in a sentence and on top of that at the meta data such as: where did the message come from? Where is it going?  What kind of responses is it getting?

“Finally, you train the model with validation data to see how good your model is. Then when it goes live you check for false positives and negatives to find out: did we miss something? The idea is the system gets smarter and smarter as you go.”