Every once in a while, we ask some random questions about email here at MailChimp. Questions like:

• Remember that blog network that just got hacked, and how all their user data was posted to the public? Wonder if any bad guys are importing that email list into MailChimp anywhere. Would be nice to shut them down, and maybe even report them to the FBI.
• Hey, what if we purchased some spam lists ourselves, and just used them to scan all users’ imported lists for high levels of correlation?
• Across all the emails we’ve ever sent, what’s a realistic “average shelf life” for a subscriber’s engagement?
• Is there a *real* “best time” and “worst time” to send email? Of course people will always say “it depends” but what if we actually crunched (all) the numbers anyway? Would we find interesting patterns?

And some questions can be real dilemmas, like:

• If user X imports a list, and we find a bunch of hard bounces, why don’t we prevent those bad email addresses from being imported into our system by user Y? (after all, lots of bounces can lead to delivery problems at some of the big ISPs)
• If we know a particular subscriber is a habitual (false) complainer, should we keep allowing them to subscribe to lists that we host? Even if there’s double opt-in proof?

MailChimp Engineers: “Shutup, already. Go look it up yourself.”

I guess all these questions finally annoyed our engineers enough to make them setup The Email Genome Project, which scans MailChimp’s 600,000 users, the hundreds of millions of subscribers they manage, and the 40 million (and growing) messages they send every day for nuggets of information that we can use to improve our deliverability and train our Omnivore abuse prevention algorithms.
The fun part of all this? The nerds get to play with cool toys…
Read More

We recently experimented with crowdsourcing the review of outgoing campaigns from MailChimp’s servers. Normally, if our Omnivore algorithms detect something suspicious about a campaign, we’ll automatically suspend the account and follow up with a review by our internal Compliance Team. But we’ve been testing the idea of also sending the campaign to Amazon’s Mechanical Turk service for manual review by humans. We simply showed the email to a “turker” and asked them, “Is this spam?”

The experiment only involved sending roughly 7,000 email campaigns over to be reviewed. But within the first 2 days, we started getting back some unexpected, yet fascinating results.

In particular, there were certain email templates that kept getting repeatedly flagged as spam by these human reviewers, even though they weren’t spam at all.

All these “false positives” had some common design traits, so we thought we should share our findings…

Read More

Earlier this week, we discussed how Gmail’s new “Priority” feature tracks engagement to judge what emails are most important, and then prioritizes them.

We also discussed how MailChimp is using engagement to decide which emails to clean from our senders’ lists.

Yesterday, we learned that Hotmail is also tracking user interaction within their inbox in order to determine which emails to throw away, and which to keep:

Hotmail Using New Metrics to Consider Inbox Placement by George Bilbrey on MediaPost

Read More

One of the hardest, dirtiest jobs we ESPs have to do is manage bouncebacks. We send a few bajillion emails out, and a kajillion bounces inevitably come back. Now, we have to scan every single one of those complicated email headers to figure out what type of bounce it was, then decide what to do with it. If we get a “hard” bounce, that usually means the account we tried to deliver email to doesn’t exist (and so we should clean the member from that list). If we get a “soft” bounce, that usually means the account exists, but we should try again later. Not to mention FBL parsing, and simply filtering out the spam that we get before we can even get to the bounces. It’s like sorting through a dumpster to find recyclables or something. Not very glamorous.

It would be all fine and dandy if people would follow delivery status notification best practices and guidelines. But they don’t. Sometimes this is a reaction to spam, and sometimes it’s just ignorance.

For example, some server admins insert snarky messages in their email headers, like “We don’t want your message. If you send email to us again, we’ll report you.” Well, that’s their prerogative and all, and we’re happy to never send to them again, but if they simply hard bounced the email, we’d be able to clean it from the list faster.

Then there are some ISPs who are downright deceptive with their bounceback codes…

Read More

In January, we announced Omnivore, our massive anti-spam research project that ran 61 trillion email data comparisons using genetic optimization algorithms in order to teach our network how to automatically detect and prevent abuse.

For those of you who don’t know, we built Omnivore in order to prepare for our big Freemium plan that we launched back on September 1st, 2009. We didn’t want to offer a free email marketing service without having a scalable system in place to protect our deliverability (not to mention the sanity of our Compliance Team).  Good thing, too.

In just under a year, MailChimp grew from 85,000 users to over 430,000. We couldn’t have grown 5-fold like that without Omnivore.

Here’s an update on what we’ve learned so far…

Read More