Feedback loops

There are a lot of different perspectives on Feedback Loops (FBLs) and “this is spam” buttons across the email industry.
Some people think FBLs are the best thing since sliced bread and can’t figure out why more ISPs don’t offer them. These people use use the data to clean addresses off their lists, lower complaints and send better mail. They use the complaints as a data source to help them send mail their recipients want. Too many recipients opted out on a particular offer? Clearly there is a problem with the offer or the segmentation or something.
Other people, though, think the existence of “this is spam” buttons and FBLs is horrible.  They call people who click “this is spam” terrorists or anti-commerce-net-nazis. They want to be able to dispute every click of the button. They think that too many ISPs offer this is spam buttons and too many ESPs and network providers pay way to much attention to complaints. The argue ISPs should remove these buttons and stop paying attention to what recipients think.
Sadly, I’m not actually making up the terminology in the last paragraph. There really are who think that the problem isn’t with the mail that they’re sending but that the recipients can actually express an opinion about it and the ISPs listen to those opinions. “Terrorists” and “Nazis” are the least of the things they have called people who complain about their mail.
One of the senior engineers at Cloudmark recently posted an article talking about FBLs and “this is spam” buttons. I think it’s a useful article to read as it explains what value FBLs play in helping spam filters become more accurate.

We have found over time that the most effective systems are those that learn to classify undesirable content based on feedback from users. The user is truly the best judge of what is and isn’t spam. The faster that consistent feedback becomes available, the sooner a filter can be re-trained to detect and respond to new attacks.

Spam filters are not there to stymie senders, their real job is to protect recipients. Faster adapting filters may seem like a bad thing, but they adapt in both directions. Send good mail that people want and it gets through. Send bad mail that people complain about and filters quickly adapt to block it.

Related Posts

Beware the TINS Army

When consulting with clients, I spend a lot of time trying to help them better understand the concept of sender reputation. Spam reports, feedback loops, and other data that comes from a collection of positive and negative reputational feedback about a company sending email.
Certainly, the “This is not spam” action – moving an email from the spam folder to the inbox, or clicking the “not spam” button in a web mail’s interface, is a strong positive reputational action. Some webmail providers use this data to decide which bulked senders deserve being let out of the penalty box – which should have their mail once again delivered to the inbox.
A client recently theorized that a great solution to their delivery problems would be to do this “en masse.” Sign up for hundreds or thousands of webmail accounts, send my mail to them, and click on the “not spam” button for each of my own emails. That’ll greatly improve my sending reputation, right?
NO! ISPs have already thought of this. They watch for this. They’re really good at picking up on things like this. I know for a fact that Yahoo and Hotmail and AOL notice stuff like this, and I strongly suspect other webmail providers notice it as well.
What happens when Yahoo or Hotmail pick up on this type of unwanted activity? Well, if it’s at Yahoo, they’re likely to block all mail from you, 100%, forever. I’ve seen it happen more than once. Yahoo might even identify all of your netblocks, ones beyond the ones sending today’s mail or originating today’s activity. And good luck trying to convince them that you’re not a spammer – you have a better chance of winning the lottery two weeks in a row.
As for Hotmail – what would Hotmail do? Ask Boris Mizhen. Microsoft is currently suing him, alleging that he and/or his agents or associates engaged in this very practice.

Read More

Botnets and viruses and phishing, oh my!

MessageLabs released their monthly report on email threats yesterday. Many media outlets picked up and reported that 41% of spam was from a the Rustock botnet.
Other highlights from the report include:

Read More

Why do ISPs do that?

One of the most common things I hear is “but why does the ISP do it that way?” The generic answer for that question is: because it works for them and meets their needs. Anyone designing a mail system has to implement some sort of spam filtering and will have to accept the potential for lost mail. Even the those recipients who runs no software filtering may lose mail. Their spamfilter is the delete key and sometimes they’ll delete a real mail.
Every mailserver admin, whether managing a MTA for a corporation, an ISP or themselves inevitably looks at the question of false positives and false negatives. Some are more sensitive to false negatives and would rather block real mail than have to wade through a mailbox full of spam. Others are more sensitive to false positives and would rather deal with unfiltered spam than risk losing mail.
At the ISPs, many of these decisions aren’t made by one person, but the decisions are driven by the business philosophy, requirements and technology. The different consumer ISPs have different philosophies and these show in their spamfiltering.
Gmail, for instance, has a lot of faith in their ability to sort, classify and rank text. This is, after all, what Google does. Therefore, they accept most of the email delivered to Gmail users and then sort after the fact. This fits their technology, their available resources and their business philosophy. They leave as much filtering at the enduser level as they can.
Yahoo, on the other hand, chooses to filter mail at the MTA. While their spamfoldering algorithms are good, they don’t want to waste CPU and filtering effort on mail that they think may be spam. So, they choose to block heavily at the edge, going so far as to rate limit senders that they don’t know about the mail. Endusers are protected from malicious mail and senders have the ability to retry mail until it is accepted.
The same types of entries could be written about Hotmail or AOL. They could even be written about the various spam filter vendors and blocklists. Every company has their own way of doing things and their way reflects their underlying business philosophy.

Read More