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

Another way Gmail is different

I was answering a question on Mailop earlier today and had one of those moments of clarity. I finally managed to articulate one of the things I’ve known about Gmail, but never been able to explain. See, Gmail has never really put a lot of their filtering on the SMTP transaction and IP reputation. Other ISPs do a lot of the heavy lifting with IP filters. But not Gmail.
While I was writing the answer I realized something. Gmail was a late entrant into the email space. AOL, Hotmail, Yahoo, even the cable companies, were providing email services in the 90s. When spam started to be a problem, they started with IP based blocking. As technology got better and content filtering became viable, improvements were layered on top of IP based blocking.

Gmail didn’t enter the mailbox market until the 2000’s. When they did, they had money, lots of hardware, and internal expertise to do content filtering. They didn’t start with IP based filtering, so their base is actually content filtering. Sure, there were some times when they’d push some mail away from the MTAs, but most of their filtering was done after the SMTP transaction. The short version of this is I never really pay any attention to IP reputation when dealing with Gmail. It’s just another factor. Unless you’re blocked and if you get blocked by Gmail, wow, you really screwed up.
Gmail does, of course, do some IP based blocking. But in my experience IP filters are really only turned against really egregious spam, phishing and malicious mail. Most email marketers reading my blog won’t ever see IP filters at Gmail because their mail is not that bad.
Other companies aren’t going to throw away filters that are working, so the base of their filters are IPs. But Google never had that base to work from. Their base is content filters, with some IP rep layered on top of that.
That’s a big reason Gmail filters are different from other filters.

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