Blog


A blog about security, privacy, algorithms, and email in the enterprise. 

Python Resources

Comment

Python Resources

By David Wihl

Python is the language of choice for many applications that collect and analyze text data, including Skimbox's email classifier. Since python was not, for me, a native tongue, I signed up for an EdX course, Introduction to Computer Science Using Python. The following list contains books, tutorials, tools, and other resources my classmates and I have found useful. If you have any to add, please do so in the comments!

Comment

Why the Unread Count Is a Worthless Number

3 Comments

Why the Unread Count Is a Worthless Number

By Brian Barnes

If you have 1,190 unread emails and you get 5 more, can you really tell the difference?  Do you often think to yourself: “I have to tackle 4567 unread emails today?” Unless you keep your inbox well-managed (and some people do) the unread count is a worthless number.

3 Comments

Teach a Man to Phish

Comment

Teach a Man to Phish

By Claire Willett

Spear-phishing, the practice of luring people in organizations into giving up control of confidential data via seemingly legitimate emails, is the contemporary corporation hacker’s bff. Why not, when all it takes is one employee clicking on one “2011 recruitment plan.xlsx.”

 

Comment

Mail Me Later

Comment

Mail Me Later

By Claire Willett

The snooze button is over half a century old, but it didn’t make a big splash in our inboxes until 2010, when a small startup baked it into a Gmail plugin they called Boomerang. Boomerang has since added a slew of other features (including some fun game-based ones) but their core value remains the same: allow you, the recipient, to decide when an incoming email should return to your inbox.

And it really is a value: it played a big role in Mailbox’s initial success, and now, the ability to defer has become almost de riguer for new mail apps, Skimbox included.

Comment

Decide for me

Comment

Decide for me

By Claire Willett

We humans use, create, and pass on metaphorical concepts (time is money, communication is sending, a right-slanted 5 is dangerous) to make quicker sense of our worlds. Vladnik’s results indicate that a computer trained on this type of experiential information can learn far faster, with far less data than one trained gavage-style. In the (perhaps very near) future, metaphor might be the defacto conduit for artificial intelligence. And if it does, I suspect that rather than rule the world, robots will help us rule our own.

Comment

3 Ways to Make Sure Your Unsolicited Email Gets Read

Comment

3 Ways to Make Sure Your Unsolicited Email Gets Read

By Paula Marciante

Templates -- honestly, they’re the number one contributor to no response. I get that you are busy and need to get information out to large number of people.  You have numbers to meet and meetings to set!  But if you don’t put in the effort to personalize some of your email even just a little, then don’t expect much back.  At the very, very least, personalize your salutation.

Comment

Skimbox for Exchange and Gmail Is Here

Comment

Skimbox for Exchange and Gmail Is Here

By David Wihl

We set out over a year ago to explore analytics for email. Part of this exploration involved getting a lot of feedback from a lot of people who got a lot of email. The main takeaway: analytics are cool, but email overload is a much greater daily battle.

Comment

Email Statistics, Visualized

2 Comments

Email Statistics, Visualized

By Claire Willett

As you can see, Gmail was by far the most popular mail service -- indeed, 7/7 surveyed used it as their primary work email, personal email, or both. Runner up was Yahoo, but in both cases, it was used as a newsletter/junk mail address. 

2 Comments

Defining Skimmable Email

Comment

Defining Skimmable Email

This is what is broken with email today: critical pieces of information that could save or enhance your job, company, or family are mixed in with coupons for sky diving lessons.  And it isn’t just marketing messages. Chances are, your own company sends you noisy email (collaboration system notifications come to mind)--email that could cause you to miss something really important.

How big of a problem is noisy email?  Pretty darn big, as it turns out.

Comment

Reading Kurzweil in Jerusalem

Comment

Reading Kurzweil in Jerusalem

By David Wihl

In 1997, IBM’s Deep Blue defeated world chess champion Kasparov, a major achievement. Amazingly, Kasparov had never lost any tournament match before to either man or machine.

Fast forward sixteen or so years, Machine Learning has become pervasive. Most significant computer interactions such as using a credit card, searching the web, shopping online, or calling customer service involve Machine Learning algorithms and approaches.

Comment

Modelers Behaving Badly

Comment

Modelers Behaving Badly

By Claire Willett

In the late 70s, a doctor on the staff of St. George’s Hospital Medical School developed an algorithm to assist with the school’s admission process. Between 1982 and 1986,  100% of the interview decisions were made by this algorithm

Comment

Hubspot, Skimbox, and the Rise of Relevance

Comment

Hubspot, Skimbox, and the Rise of Relevance

by Claire Willett

My biggest takeaway from Inbound had nothing to do with A/B testing or workflows. Rather, it was:

Bespoke is the new one-size-fits-all.  

Before I dig into that, a little background: Hubspot's core philosophy is "if you build it, they will come--and convert." 

Comment

PRISM vs. On-Premise Email

Comment

PRISM vs. On-Premise Email

BY Claire Willett

It’s safest to assume that any email, sent from any service, will be monitored. However, for corporations seeking some control over who has access to their employees’ inboxes, there is a bright light, and its name is "on-premise email."

Comment

The Phone that Cried Wolf

Comment

The Phone that Cried Wolf

I’m sure everyone is familiar with the parable "The Boy Who Cried Wolf."  Quick reminder: there was a boy tending sheep in the fields away from his village.  Boredom and loneliness got to him, so he cried something along the lines of: "help, there is a wolf" and everyone in the village came to save him.

Except, of course, there was no wolf.

Comment