Engagement filters for B2B mail

While I was doing some research for a client today I rediscovered Terry Zink’s blog. Terry is one of the MS email folks and he regularly blogs about the things MS is doing with Outlook.com and Office 365.
The post that caught my eye was discussing the Microsoft Spam Fighter program. The short version is that in order to train their spam filters, Microsoft asks a random cross-section of their users if the filters made the right decision about email. This data is fed back into the Microsoft machine learning engine.
As Terry explains it:

These votes from all the users across the entire Spam Fighters program are combined, and the messages combined to create a corpus, and then Smartscreen learns across numerous features within a message – sending IP, sending domains, authentication status, headers, body of message, attachments, encodings, and so forth. This feeds into our IP reputation, and into the Smartscreen spam filtering algorithm. This algorithm is what does the filtering for spam, malware, and phishing as well as legitimate email. It’s updated multiple times per day.

The SmartScreen filter is a source of pain for many senders. But, Microsoft checks it’s accuracy on an ongoing basis. When Microsoft says that SmartScreen data tells them this mail is unwanted, they are getting that information directly from the subscribers of the email. If the subscribers don’t want mail, it’s nearly impossible to get ISPs to deliver that mail.
Engagement based filtering is standard in the consumer space. The primary mailbox providers focus on providing their users with the mail that they want, while protecting them from malicious mail. Things are different in the business space as most business filters don’t care if the user engages with the mail or not. For businesses email is a tool and sometimes we don’t like our tools.
However, as Microsoft merges the backend for Hotmail/Outlook and Office365 engagement filtering may become more relevant at those domains hosted on Office 365. I don’t expect those filters to be identical – again these are different user bases with different priorities. But Smart Screen filters may start acting on business email in the future.

Related Posts

Filtering more than spam

The obvious application of machine learning for email is to send spam to the junk/bulk folder. Most services use some level of machine learning for filters. Places like Gmail have extensive machine learning filters to filter spam and unwanted mail away from their users.
Some organizations are taking the filtering process a step further. Almost every mail client more advanced than PINE has the ability for users to create rules to sort mail into folders.  Late last year, Office 365 rolled out a feature, Clutter that tracks how a user interacts with mail and filters unimportant mail. This allows each user to have their own filters, but without the overhead of having to create the filters.
The Clutter engine looks at both how the user interacts with mail and things it knows about the organization. For example, if Exchange is tied into Active Directory, then mail from a manager will be prioritized while mail from a co-worker may end up in the clutter folder.
Email is a critical business tool. A significant number of companies rely on email for internal and external communication. Many users treat their inbox as a todo list, prioritizing what they work on based on what’s in their mail box. Despite the needs of users, the mail client hasn’t really changed.
Over the last few years, we’ve seen different online services attempt to build a more effective email client. Some of these features were things like tabs and priority inbox at Gmail. Microsoft created the “sweep” feature for Outlook/Hotmail users to manage inbox clutter. Third parties have created services to try and improve the mailbox experience for their users. 
Many of the email filters, up to this point, have really been focused on protecting users from spam and malicious emails. Applying that filtering knowledge to more than just spam, but to the different kinds of emails makes sense to me. I’ve always had a fairly extensive set of filters, initially procmail but now sieve, to process and organize incoming mail. But I kinda like the idea that my mail client learns how I filter messages and do the right thing on its own.
I’d love to see some improvements in the mail client, that make it easier to manage and organize incoming email. It remains to be seen if this is a feature that takes off and makes its way to other clients or not.
 
 

Read More

Getting unblocked at Outlook.com

It’s been a crazy week here at M3AAWG. I have a lot of stuff to blog about, but I think one of the really important things to get out is the new unblock request page at Outlook / Hotmail.
https://sender.office.com
Submit your IPs and it will be reviewed.
(Apologies for the repeated bad links. I’m blaming con crud, lack of sleep and MSN/Hotmail/Office/Outlook for having so many domains I can’t keep them straight. I have finally gotten it right and tested it.)

Read More

Microsoft deprecating SmartScreen filters

At the beginning of the month Microsoft announced that they were deprecating the SmartScreen filters used by the desktop Microsoft mail clients. These are the filters used in Exchange and various version of Outlook mail. This is yet further consolidation of spam filtering between the Microsoft free webmail domains, Office365 hosted domains and self hosted Exchange servers.  The online services (hotmail.com, outlook.com, Office365, live.com, etc) have been  using these filters for a while. The big change now is that they’re being pushed down to Exchange and Outlook users not hosted on the Microsoft site.
EOP was developed for Outlook.com (and friends) as well as Office365 users. From Microsoft’s description, it sounds like the type of machine learning engine that many providers are moving to.
Microsoft has published quite a bit of information about these filters and how they work on their website. One of the best places to start is the Anti-spam Protection FAQ. Something senders should pay attention to is the final question on that page: “What are a set of best outbound mailing practices that will ensure that my mail is delivered?” Those are all things  deliverability folks recommend for good inbox delivery.
Poking around looking at the links and descriptions, there is a host of great information about spam filtering at Microsoft and how it works.
A page of note is their Exchange Online Protection Overview. This describes the EOP process and how the filters work.
MS_filterProcess

Read More