A deep dive into the impact of automation and technology on jobs

I spent some time over the weekend, (I know, I probably need some other hobbies), reviewing a new report from the Brookings Institute titled 'Automation and Artificial Intelligence: How Machines are Affecting People and Places'. In the report, Brookings sought to examine (like plenty of other organizations in the last few years), what the potential impact of advanced technologies, automation, and AI will be on the labor market. Mainly, which kinds of jobs and in what areas are more or less likely to be affected, changed, and potentially replaced as technology continues to improve and advance.

There is a ton of interesting information in the 100+ page report, and for those of you who are interested in this sort of thing, I would block some time to go through it all, but for those who may want a shorter, TL;DR version, here are what are to me, the three most interesting findings/conclusions/takeaways from the report.

1. Contrary to a lot of hype and hysteria around automation and AI, most jobs are not highly susceptible to automation. Take a look at the key finding from Brookings in the chart below:

While almost no single occupation will be completely unaffected by the adoption of new technology, the impact on jobs will be of varying intensity and significant for only about 25% of jobs. Another 52 million or so jobs, about 36% of the labor force will see some or medium impact from new tech. And another 39% of jobs will only see a low impact from new technology. This disparate impact on jobs reminds me of the old saying, 'The future has already arrived, it's just not evenly distributed'.

2. Lower wage jobs are, on average, more exposed to potential automation. Within the variability expressed in the first chart, Brookings tries to break down what kinds of jobs, at what kind of wages, and in which geographic areas are most prone to be impacted by technology. Here's a look at the data around wage level and potential impact from automation:

The main driver behind lower wage jobs being more susceptible to automation is the tendency for jobs made up largely of routine, predictable physical and cognitive tasks are the ones most vulnerable to automation in the short and medium term. Think jobs like office administration, simple production, and food preparation. So according to Brookings the roles that now tend to pay the lowest wages are at the most risk. The danger of this of course is that the people holding these jobs also tend to be the least prepared to make a job shift into roles that are more complex, higher up the wage scale, and less likely to be impacted by technology.

3. In addition to varying widely across types of jobs and wage level, automation of jobs is likely to vary widely by location as well. The larger relative impact will be felt, according to Brookings, in smaller, and more rural areas. See the data below:

There's a lot of detailed data to parse through there, but basically workers in smaller and more rural communities are about 10 percentage points more likely to have their jobs adversely impacted by technology than workers in urban areas. This could be a by-product of the continuing challenge that smaller communities have in keeping their skilled and younger workers from leaving to seek better opportunities in larger towns and cities.

Since this is a long post already, I will leave covering what the folks at Brookings suggest can be done by localities, companies, education, and people in order to be better prepared for the ongoing waves of automation. Suffice to say though that understanding the problem and challenge is the important first step to solving it.

Take some time to look at the whole report if you can.

Have a great week!

CHART OF THE DAY: ETFs, Active Managers, and Human Specialization

Today's Chart of the Day comes to us from the world of Finance and our pals at Bloomberg and shows just how once type of job, the "active", (and human) mutual fund manager is being disrupted by another kind of manager - a 'passive' one, modeled against the market more broadly, and dominated by algorithms and sophisticated computers.

Long story short - investors have been migrating their money away from the active, people-driven funds and strategies and towards the passive, ETF-type funds. Here's the chart from Bloomberg, then some comments below from your favorite active blog manager (me).

Some really interesting things to note from this chart. And recall, just like when we blog about basketball here, this blog about finance and investing isn't really just about finance and investing.

1. Highlighted on the chart is the worst of the financial crisis, September 2008. This appears to be the inflection point where investors bailed on active investment management in favor of passive investing. In other words, when times were tough, investors didn't seek 'expert' human management for their diminishing funds. In fact, they sought out the opposite.

2. As the chart above demonstrates, the current active management model for investments simply can't compete any longer with the cheaper passive/ETF model in either total asset gathering (trying to simply grow the way to prosperity), or in terms of returns. Whatever the current strategy is for the active managers, it is definitely not working and has not been for a decade.

3. So what can these highly-paid, expensive, and under threat active fund managers do to at least try and maintain some relevance and hold on to their country club memberships and beach houses? Bloomberg suggests one approach - hyper specialization.

From the piece:

What does the future of active management look like? We believe it should only seek a portion of an investor's assets. To do this, they will have to create highly idiosyncratic and concentrated portfolios. They will have to find the one thing they do well and do it in a concentrated, risk-seeking way, whether it be health-care, emerging markets, macro themes, algorithms, technology or trading. The manager will need to be known as the "go to" person in that space to emerge as the next star, allocating capital as efficiently as possible.

Again, the specific example/industry/job role doesn't matter here. What matters is the method and approach for people to remain valuable and competitive in a situation where machines and algorithms have plenty of advantages. The advice is not to try and out-compete the robots where you simply can't defeat them, but rather to seek out those areas, pockets, and opportunities where you can leverage uniquely human skills and experience to stay one step ahead of the machines.

Super interesing article and one that I think no matter what industry or job you are in, has something we can learn from as well.

Have a great day!

It doesn't matter if the robots aren't coming for your job, they are coming for your neighbor's job

After reading a flurry of pieces over the last few days about the progress being made in self-driving vehicle technology, I was reminded that one job category that seems likely to be highly pressured by this type of automation is commercial vehicle driving. You don't have to be a genius to realize that once Tesla (and others), get enough of their new commercial trucks into service, that Generation 2.0 of these trucks will attempt to not just eliminate diesel fuel and noxious emissions from their products - they will try to eliminate the driver too.

And you probably caught something about Amazon's newest experiments with retail stores that have no cashiers. Or maybe you have heard about fast food giants like McDonald's or Panera pushing more self-service kiosks into their locations, to reduce the need for human cashiers and order-takers. Or the hotels that are using mobile robots to deliver room service meals to their guests. And the list goes on and on.

And maybe after reading all these stories you say to yourself: "Self, these technology advancements are amazing. But good thing I am a (insert the white collar 'knowledge' job you have here) and not a truck driver or a cashier.' 

And whether or not the robots are coming sooner or later for whatever 'knowledge' job you have today is probably debatable, let's pretend for the moment in the words of Big Brother, (yes, I am fan), - 'Knowledge worker X, you are safe'. Phew. That is a relief.

But here is the thing, the kinds of jobs that are most vulnerable, most likely to be adversely impacted by automation are ones that are held by millions of people. Have a look at the chart below, from BLS data from May 2016.

Look closely at that list of the Top 10 'most-held' job categories in the US and think about which of them, (Clue: It is almost all of them), are going to be increasingly pressured by technology, automation, and 'self-service'.

There are about 150M people in the US labor force give or take. The Top 10 job categories in the above chart represent about 21 or 22 million workers - roughly 15% of all US workers. That is a huge number, especially considering that half a percent or a full percent moves in the unemployment rates are such big news.

The potential and the consequences of labor automation are concerns for everyone - whether or not your job is 'safe'.

And one last bit of food for thought. This issue, this challenge of automation and technology threatening jobs is also going to be a local one. Check out this chart below that shows the largest private employer for each state in the US. See any cause for concern?

When Walmart decides to move more aggressively into online, self-service, robot customer service pods, and Amazon-like efficiency in their distribution centers there will be an impact too.

But that's ok. You don't work at Walmart.

But I bet you know someone who does.

Self-driving bus crashes, proving all buses should be self-driving

In case you missed it, a fairly significant pilot of self-driving vehicles, in this case shuttle buses, launched last week in Las Vegas. In this test, shuttle buses developed by French company Navya ARMA will carry passengers along a half-mile route in downtown Las Vegas, (that part of Vegas that most of us who go to Vegas for Conference and conventions tend to ignore). The Navya ARMA buses rely on GPS, cameras, and light-detecting sensors in order to navigate the public streets. According to reports, the year long test hopes to shuttle about 250,000 passengers up and down the Vegas streets.

Pretty cool, right?

Guess what happened in the first couple of hours after launching the self-driving pilot program?

Yep, a CRASH.

The first self-driving bus was in a minor accident within a couple of hours of the service's launch when a (human driven) delivery truck failed to stop in time and collided with the stationary shuttle bus.

According to a spokeperson from the American Automobile Association, "The truck making the delivery backed into the shuttle which was stopped. Human error causes most traffic collisions, and this was no different."

No one was hurt, the damage was minor, and the self-driving pilot program continues in Las Vegas.

Why bring this up, especially on a blog that at least pretends to be about work, HR, HR Tech, etc.?

Because these kinds of technology developments, of self-driving vehicles, robots that can sort and organize inventory in warehouses, robots that will greet and provide basic customer services in retail environments and hotels, are being developed, improved, and deployed at increasing rates and in more and more contexts.

Self-driving technology in particular, especially for commercial vehicles, is by some estimates within 10 years of becoming a mainstream technology, potentially displacing hundreds of thousands of commercial truck drivers. And as an aside, this piece describes how the trucking industry is clearly not ready for this and other technological disruptions.

This is not meant to be another, tired, 'Robots are taking our jobs' post, but rather another reminder that technology-driven disruption will continue to change the nature of work, workplaces, and even our own ideas about the role of people in work and the economy. And HR and HR tech leaders have to take a leading role in how, where, when, and why their organizations navigate these changes, as they sit directly at the intersection of people, technology, and work.

And lastly, if that Las Vegas delivery truck had been equipped with the same kinds of self-driving tech that the Nayva ARMA bus has, there is almost no chance there would have been an accident.

But it might have be fun if it happened anyway. I'd love to see two 'robot' trucks argue with each other on the side of the road about which one was the doofus who caused the accident.

Have a great day!

Basketball, media, and robots coming for our jobs

With the events of last week's election pretty much consuming and subsuming national attention last week you probably missed this really interesting story on the intersection of sports, media, and technology, one that raises some interesting questions about the future or automation and work.

First a little background on the story from last week, then some thoughts on why it is interesting beyond the narrow, 'sports' focus.

Last week Mark Cuban, famous rich guy and owner of the NBA's Dallas Mavericks suddenly revoked the media credentials at Dallas' arena for two Dallas based ESPN basketball writers, Mark Stien and Tim MacMahon. From the first reports that came out, Cuban made the decision to revoke the ESPN pair's credentials because he was disappointed that MacMahon would not be covering every Mavericks game, a change from prior years; and Stein, as a national NBA reporter was thought to only want to cover Mavs games to gain access to players and coaches from the Mavs opponents as they came through Dallas. It was reported that Cuban was particularly miffed by the fact that no ESPN media attended and reported on the Mavs opening night game.

If this story was just about a team owner trying to play strong arm a major media outlet into providing more coverage for his team, it would not be all that interesting, and I would not have decided to write about it here.

But a day or two after the initial media credential ban was announced, the story became more nuanced, and well - interesting. 

What Cuban was also protesting, in addition to the reduced coverage of Mavs games in general by ESPN, was what he feels like is going to be the inevitable replacement for at least some human media game coverage - automated game summaries and stories generated by machine learning and algorithms.

Here's some additional detail from an email Cuban sent to the web site Deadspin, who had been reporting on the Mavs-ESPN kerfluffle: (Note: I edited this some for brevity and clarity, the full email is at the link above)

Two things triggered this whole thing. First was when I found out they (ESPN) had cut back or had always offered reduced coverage for 19 nba teams I had no idea this was going on

The second was when espn didn’t cover our opening night and the resultant coverage on their website was a tweet, One highlight and a wire service story

It made me realize that I had expected to be covered by all media, but it no longer was a given

Even though espn was covering the same number of games, if they didn’t think it was a big deal to miss opening night. I had a problem. Not necessarily an espn problem , but a coverage problem

And if it’s 30 games now for 19 teams. What would keep it from being 60 games for 25 teams ?

What was their long term thinking ?

When you realize that the hottest area in technology, and it’s not even close , is machine and deep learning , then it’s an easy step to see where this was going

I told espn this was my concern. They didn’t say they were taking this path. They didn’t say they weren’t. But I voiced these concerns to them

They said they would run their business . I can run mine

So the next question is where would it leave Mavs fans who wanted game results coverage of nothing changed and espn didn’t send a reporter for 30 games ?

It meant for 30 games and inevitably more in the future they wouldn't have a good experience with espn

It meant it was likely that in the near term when they went to espn Dallas they find a couple videos, tweets and a wire service story

How is that positive for any nba team or their fans when 30 games have second rate coverage ?

And what happens and what message is sent to fans when those games are covered by an algorithm in the future ?

Short term this is a Mavs issue. Long term it’s a certainty that our games will be covered algorithmically. Thats a problem across the board for us and the NBA

IMO that devalues our brand . It devalues the fans experience. I feel strongly that now is the time to partner with those who commit to the Mavs and to sending real people to cover the games for Mavs fans

It may seem like we are picking on espn or telling them how to run their business. We aren't. We are trying to protect ourselves and our fans and our future by partnering with those in the written media who commit to us

I know the whole automation thing may not make sense to some. But to me this is no different than saying that streaming would change media in 1995. Or social media would change coverage of sports , etc

Machine and deep learning and algorithmic coverage of sports events is going to happen.

This isn’t about replacing writers. The best writers will always have a place

This comes down to how do we value reporting on a game . Right now I value it more than espn and others and want to partner with the DMN FWST (media outlets), and use our own writers as our focus

Really interesting takes coming from a guy who got rich back in the day, selling a technology company, (Broadcast.com) for millions to Yahoo. Cuban is no Luddite or technophobe.

But at least in 2016, he (probably rightly), feels that despite advances in machine learning and automation that NBA game coverage is still best produced by actual human reporters and not the algorithms. And if you think that the entire idea of an algorithm replacing a human reporter to write sports event coverage think again - it is already happening mostly via technology created by a firm called Automated Insights. You can learn more about what they are doing with automated reporting of minor league baseball games here.

Let's go back on one line of Cuban's email above - "Long term it’s a certainty that our games will be covered algorithmically. Thats a problem across the board for us and the NBA."

In the same message where Cuban admits to using some tough negotiating tactics to push ESPN to continue to provide quality, human coverage of Mavs games, he admits that the algorithmic coverage of these games are a certainty. Today while technology like the one provided by Automated Insights is inferior to human reported coverage, over time it seems apparent to Cuban that the difference in quality will matter less to the media company than the sheer cost savings and efficiency gains that could be realized by replacing human reporters with a computer program.

And Cuban has a problem with that, as it is in his best interests to have top-notch coverage of Mavs games in the media, as he sees that as an extension of his team and of the Mavs brand.

I know this post has gotten pretty long, especially for a busy Monday, but I thought it important enough to try and lay out the context before hitting what I think is the main takeaway which is this:

Just because something can be automated away or a job be done by a robot or a machine instead of a human doesn't mean that it necessarily should. Your customers will decide and balance the tradeoffs between costs, convenience, and quality about the products and services you are offering. 

You might think, or your CEO might insist, that automation is always the way to go, but until the robot or the algorithm can do the job almost as good as the human it is replacing, then don't be too quick to agree.

Think I am wrong?

Take a look at the 'self-service' checkouts sometime at a busy grocery store or big box home improvement retailer?

Anyone using those? Do they provide a great experience?

Or would you rather wait an extra few minutes and check out with a human cashier?

Have a great week all!