Jun 232005

Sender Score: Credit Scores for Emailers

Sender Score:  Credit Scores for Emailers

Yesterday, I wrote about email authentication, and why, although it’s great, it won’t stop spam without the emergence and scaling of accreditation and reputation systems.

Today, Return Path has announced the beta launch of Sender Score, our new reputation management system.  Sender Score is a groundbreaking service that we’ve been working on for a long time here.  The best way to think about it (or the analog analog, as Brad might say) is as a FICO or credit score for email.

We’ve gone out and compiled TONS of data about emailers, much as the credit bureaus do when they gather financial profile and transaction data about individuals and businesses.  But our data, when aggregated and modeled, represents an emailer’s reputation — are they a “good risk” to let into your email network, or are they a “bad risk” to be treated separately?

What kind of data?  It’s the same data that ISPs and sys admins use to block and filter most emailers…variables such as complaint data, e-mail send volume, unknown user volume, security practices, identity stability, and unsubscribe functionality.  The system tracks 60 different data points and draws data from a diverse sample of more than 40 million email boxes.  The data comes from lots of different places, some from our own systems, and some from partner ISPs and other tech/filtering/data companies we’ve partnered with such as Cloudmark and Lashback.

This is powerful stuff.  The main thing we do with the data is provide it back to email marketers and publishers in a format that’s easy to understand and act on.  It’s like the free credit report many banks offer their customers so their customers can see themselves as potential creditors see them, then work to shore up the weak spots in their profile so they’re more likely to get the next loan/mortgage/approval.

Sender Score rounds out our Delivery Assurance offerings by adding reputation management to accreditation, monitoring, and professional services offerings.  With authentication gaining steam out there as a backdrop to all of this…we’re a lot closer to solving spam and false positives than we’ve ever been.

Filed under: Email

Tags: , ,

Feb 242005

Spam, Hot Spam, Now Only $0.10 Each!

Spam, Hot Spam, Now Only $0.10 Each!

By now, you may have seen news of the report from Ferris research citing the annual global economic impact of spam at $50 billion (apparently the U.S.’s share, $17 billion, is 0.17% of our gross national income).

I have no doubt that spam is an expensive problem.  IT managers and sysadmins spend lots of time dealing with it, and much hardware, software, and bandwidth are consumed.

But the one number that strikes me as odd in the report is that the economic impact of not having a spam filter (i.e., manually filtering spam, more commonly known as hitting the delete key) is $718 per user per year.  I guess it depends how you measure cost, but since the average user — not people who live on email like people who, oh, say, work at an email company or who blog compulsively — only get something like 20-30 emails per day, even if most of it were spam, that cost translates into something like $0.10 per spam.  That’s a lot of economic cost associated with a push of the delete key.

Interestingly, the antidote to the $718/year problem is a good desktop filter product like Cloudmark’s SafetyBar, which costs something like $30/year.

Filed under: Email

Tags: ,

Sep 152004

Spam: Crisis, or Approaching Denoument?

Spam: Crisis, or Approaching Denoument?

A few interesting comments on this front today. Fred says the crisis is over, everyone should just calm down. Pamela says spam filtering technology is getting really good now. And I had lunch with Saul Hansell from The New York Times today, who thinks that authentication will make a monumental difference.

[For those of you who read OnlyOnce and aren’t super technical, authentication is the newest trend that ISPs are starting to employ to snuff out spammers. In a nutshell, it’s a technology like Caller ID that lets an ISP verify who’s sending the mail so they can shut it down if the mailer is clearly a bad guy (or someone who blocks Caller ID).]

I’m not sure as Fred says the crisis is over — but I think it’s on the way to being minimized. And Pamela’s right — filters like Cloudmark are pretty darn effective. Things like that just need to be rolled out to broader audiences. And Pamela’s also right that mailers will have to work on managing their identity and reputation in order to cope with new technologies like authentication and beyond. That’s a posting for another day.

But before we declare victory, let’s remember two things:

– First, these things take a LONG time to trickle down to a broad enough audience to say “problem solved.” I mean YEARS.

– Second, the bad guys aren’t going to give up without a fight. This is war! They’ll be back and they’ll find us. They’ll get better at avoiding filters, and they’ll infiltrate things like authentication and exploit loopholes in CAN-SPAM and other legislation. Remember, spam’s economics still work.

So I’m happy to say Spam isn’t still in Crisis Mode, but it’s not resolved either — how about Approaching Denoument?

Aug 052004

Baby and Bathwater Redux

Katie Hafner’s article in the New York Times Circuits section today about spam and false positives is right on the mark. Spam filters are still evolving, and spammers are evolving right with them. Although the flood of spam is largely stemmed by a good filtering app, the results for consumers are still spotty: false negatives are irritating, false positives can be very painful (as the article suggests), and the process still consumes a little too much time. While the article nails the consumer problem, it does miss the corresponding business problem around false positives (see below).

But things are getting better. While I wrote generally about how email is here to stay a couple weeks ago, there are a couple other things I’d point out after reading Katie’s article that are making the email landscape a brighter place of late:

First, even better than the Bayesian style filters referenced in the article are community-based filters. The leading one is run by Cloudmark and is called SpamNet. SpamNet relies on a community of 1 million hardcore email users voting on whether email is spam or not. I’ve used SpamNet for over a year now, and while it’s not perfect, it’s pretty good at reducing both false positives and false negatives to a tolerable level, and it’s very easy to use (but only with Outlook for now).

Second, a few companies in the email industry — Ironport (Bonded Sender) and Return Path included — are hard at work on solutions to the false positive problem that won’t leave false negatives behind. Once these solutions reach maturity (still 6-12 months away), I think consumers will notice a quantum leap improvement in managing their inboxes.

Finally, one thing I’m always trying to encourage people to realize is that this problem is not just an annoyance for them personally…but it’s an annoyance to legitimate businesses everywhere. Businesses who uses email to reach their customers — when customers request the email — are consistently finding that anywhere from 5 to 50% of their emails are blocked or filtered (with an average of 19%, according to our research). Talk about an ROI buzz kill and a CRM nightmare!

So hang onto those babies out there, consumers and marketers alike…the bathwater really will go down the drain soon!