Sponsored Content

Virtual Canary in the Digital Mine #4: Total Pre-Cull (Part 2 of 3), or, How I Learned to Stop Worrying and Love Predictive Coding

In a land that is right here and in a time that is right now, a technology has arisen so powerful that it can replace basic human document review. Is it time to bow down before our new robot overlords? Last time I regaled or, alternately, disgusted you with a tale of my days as an objective coder. We covered such weighty topics as mind-numbingly repetitive labor, mind-pummelling attorney billing practices, and the prehistory of the human-computer-interface that is my beautiful two-year-old Apple fan-girl daughter. As I said, that was about context. About trying to establish a context in which you might find the introduction of a “predictive” technology to not be such an unwelcome thing. Let’s stop for a second and consider a handful of predictive technological sidekicks that are so useful (if occasionally a nuisance) we no longer consider them innovative because they are, in fact, essential. Here’s a short roll call: • Spam filters • “Adult” content filters • Explicit image searches • Targeted advertising • iOS’s auto-correct.

By AccessData  
on

In a land that is right here and in a time that is right now, a technology has arisen so powerful that it can replace basic human document review. Is it time to bow down before our new robot overlords?

Last time I regaled or, alternately, disgusted you with a tale of my days as an objective coder. We covered such weighty topics as mind-numbingly repetitive labor, mind-pummelling attorney billing practices, and the prehistory of the human-computer-interface that is my beautiful two-year-old Apple fan-girl daughter. As I said, that was about context. About trying to establish a context in which you might find the introduction of a “predictive” technology to not be such an unwelcome thing.

Let’s stop for a second and consider a handful of predictive technological sidekicks that are so useful (if occasionally a nuisance) we no longer consider them innovative because they are, in fact, essential. Here’s a short roll call:

• Spam filters
• “Adult” content filters
• Explicit image searches
• Targeted advertising
• iOS’s auto-correct.

I know, I know. You’re thinking, “Wait, I thought he was going to try and convince me that predictive coding is a good thing”. And, sure, we’ve all missed an important email because the spam filter caught it. Or we’ve tried to do a legitimate search for, I don’t know, “chicken breasts”, only to be foiled by an overzealous content filter. Or we’ve attempted to use an explicit image search to filter out, ahem, questionable scenes only to find that the filter really didn’t understand that that picture was a picture of that. Oh my. We’ve also been persistently irritated by Google’s insistence that a “recommended” site for us might be this when actually we were looking for this. And the pithy things I can say about autocorrect would literally write themselves if I were using my iPhone to write this.

So, why would I, as the boxers say, lead with my nose? Because these examples are all hilarious exceptions to the rule otherwise established by the widespread adoption of these technologies. The rule (Virtual Canary Rule #4080) is that “you can absolutely teach a machine to think like a human when the human task it’s asked to replicate is a very mechanical process”. The spam filter, just like you would, sees an email from an address that does not look like a real person’s address or a message with a suspiciously generic subject and it trashes them. And, when it first gets started, you know that it’s wise to keep an eye on it, or at least to check when an email you expect never arrives. If you find something that you value more than the machine predicted you would, you say to it, “this is not spam”. At that point, it writes a new rule for itself and no longer trashes emails from that source. The machine has learned to think like you. And you rejoice. What’s more, when you went to look for the missing email, you saw exactly what had been going on the spam filter all this time without your input. And again, you rejoiced: you never had to look at all that garbage with your precious human eyes.

Sponsored

And that, my friends, is predictive coding. Truly the future is here and, as always, it turns out that it’s been here we us all along. When we talk about “Technology Assisted Review”, it’s nothing new. It’s simply litigation-grade spam filtering. You do a bit of preliminary review on a representative sample and your new high-tech best buddy (think C3PO) says, “Oh, I see, if you like these 1,000 documents as potentially relevant, then I recommend you also focus on these 10,000. You’re going to love them! And, please, don’t waste too much of your time or your client’s money on those 90,000 documents over here. I’m 98.769% sure there’s nothing there for you and I’ve put a little flag on them to remind you later.”

Next time, I’ll complete this trilogy by discussing just how the predictive coding engines work and present you with some recent case law not only validating but also mandating that we defer to the machines. Before then, please use this once amazing technology (I’m referring to the hyperlink) to transport yourself to my company’s entry into the predictive coding arena. Or, if you’d rather watch the tool in action, sign up here for a free live webinar.

As of this printing, we do still use actual humans to demonstrate the power of the tool.

Sponsored

Topics

, , , , ,