Companies added jobs for the 97th straight month — and the economy has now grown for 112, on track to match the longest economic expansion in American history (120 months ending in 2008). For the second-straight month, U.S. joblessness is 3.7%, the lowest in 49 years. And wages are up 3.1% year-on-year, the highest rate since 2009.

• These are all signs yet again of a red-hot economy, set into motion by the $787 billion economic stimulus in 2009, and fired up again by last December's $1.5 trillion tax cut.
• But there are counter-signals, too: Wage growth is beating inflation, for instance, but — for reasons no one has convincingly explained — it still refuses to break into the solid gains of the booming late 1960s and early 2000s.
• Wage "growth rates are below historical averages but increasing," Laurence Ales, an economics professor the Tepper School of Business at Carnegie Mellon University, tells Axios.

Americans are working hard, but still not at historical rates: The average workweek rose to 34.5 hours from 34.4 hours in September. But the so-called labor force participation rate — a broad measure of how many prime-age people are working — was 62.9%, which is higher than recent lows but still among the smallest number in four decades.

One troubling aspect is that young men are not fully part of the boom:

• Despite the economic conditions, fewer men between 25 and 34 years old are working — or looking for work — than before the financial crash, writes Bloomberg's Jeanna Smialek.
• In 2008, their labor participation rate was 86.8%; now it's 86.1%.
• If these men were working at the same rate as a decade ago, 500,000 more would be on the job, or looking for one.

On a broad level, the economy is cooling: Next year, GDP growth is forecast to steadily shrink as the effect of the tax cut wears off. Meanwhile, the Commerce Department said today the U.S. is exporting less for the fourth-straight month, and the trade deficit with China rose again to a record $40.2 billion.

In October, U.S. stock markets marked their worst month since 2011. The S&P 500 fell again today by 0.63% to 2,723.

The forecasts for what comes next are all over the map — but recession is a common theme, Axios' Courtenay Brown reports.

• Megan Greene, chief economist at Manulife Asset Management, expects a recession after 2021.
• But it could be as early as next year, according to Mark Yusko, founder of hedge fund Morgan Creek Capital. He puts the odds at 100% — thanks to trade tensions.
• “The trade rhetoric is one of the dumbest things in the history of all administrations and it will cause a global recession,” Yusko said at a recent investment conference.

Once, a misguided tweet or racist Facebook post from years ago might have avoided a hiring manager’s notice. But now, artificial intelligence is leaving no tweet unread in the search for job candidates' bad online behavior.

Axios' Kaveh Waddell reports: Companies are placing applicants under a high-powered microscope as they seek to avoid hiring employees who might create a toxic environment or harm the firm's image. But it's also limiting employee opportunities.

In February, the NYT fired writer Quinn Norton within hours of announcing her hiring. In that time, several old tweets surfaced in which she had used or amplified racist and homophobic slurs.

• The Times said it had not previously seen the tweets — several needles in a haystack of Norton’s nearly 90,000 messages.
• This is the sort of public fiasco companies would rather avoid. But while HR can’t sift through a candidate’s entire Twitter timeline, a machine can.

Enter the algorithms. Several companies offer to set the pattern-matching power of AI on the social feeds of job hopefuls to uncover posts that are racist, sexist, violent, or otherwise objectionable.

• Fama contracts with about 100 companies, each with more than 1,000 employees. For each online check, it returns a report with links to offending posts.
• Last month, Predictim began offering a similar service to parents seeking babysitters. The company goes further than Fama, asking candidates for permission to access their private posts and comments in addition to public ones. The resulting report — a sample is available here — assigns risk scores ranging from 1 to 5, overall and for categories that include drug use, bullying, and "bad attitude."

Privacy advocates worry that such systems can make basic mistakes with lasting effects.

"The automated processing of human speech, including social media, is extremely unreliable even with the most advanced AI. Computers just don’t get context. I hate to think of people being unfairly rejected from jobs because some computer decides they have a 'bad attitude,' or some other red flag."

AI-powered hiring systems can be extremely susceptible to bias.

• If a system is fed hiring data and learns that male candidates are hired more often than female ones, it can start to favor men, like an AI program Amazon tested.
• To avoid this trap, Fama and Predictim withheld sensitive information like gender and race from the training data, so their AI systems evaluate only the contents of social media posts.
• Users of Predictim, the month-old babysitter-checking service, have already run about 300 scans, said CEO Sal Parsa. Of those, 10% were flagged as moderately risky or higher, and 2.7% as very risky.

Both companies’ CEOs told Axios they work to minimize bias by carefully choosing training data, using a diverse group of people to label it, and regularly testing outputs for fairness.

The week passed you by? Never mind — catch up now with the best of Future:

1. The BRICs crash: The last domino falls in the once-hallowed group

2. The great family exodus: No room in the city for kids

3. The curse of bigness: Disturbing likenesses to the Gilded Age

4. English has the scientific edge — for now: Tech is eroding it

Social scores and now customer scores (Khadeeja Safdar — WSJ)

Homelessness and big tech (Kia Kokalitcheva — Axios)

Belief in ghosts (The Economist)

Sexual harassment threatens engineering (C.D. Mote Jr., Sheila Widnall, Ed Lazowska — IIIE Spectrum)

Politics and the secrets of Tolkien (Eliot Cohen — The Atlantic)

Homes in a box are not new — a century ago, Sears sold them by the droves for as little as $452, the equivalent of $11,600 today. Even if you went deluxe and splurged on a $2,500 model, in today's money you were only in for $64,000.

What erstwhile homeowners today would give for such bargains, Carl Franzen writes at Quartz. Home prices exceed median income in 18 of 33 countries surveyed by the IMF.

• With no answer in sight, look for a change in how housing is arranged. Just as we are moving into an age when many of us won't own our own cars, but pay a fee to share one with our neighbors, we may shop with firms that do "housing as a service."
• That could mean renting, decorating, moving — and yes, buying — all provided by big companies like Amazon, which will install smart devices to collect ever-larger troves of data for their main businesses.

The bottom line: We will see a vast whittling down of the 1.3 million U.S. real estate agents who earn a 6% commission on the homes they sell. But in urban America, home as a service may be the only way to get into a house.