IBM Watson Perfume: The Odor of Burned Cash?

November 7, 2018

Some scents are elusive. For example, what’s the odor of burned hundred dollar bills? A team locker room after a devastating loss? A failed start up’s empty cube?

The problem of elusive odors may have been solved. I learned in “Is AI the Future of Perfume? IBM Is Betting on It” that:

IBM has developed a scent algorithm, and it’s coming for the fragrance aisle.

Enticing? You bet. The write up explains:

IBM developed an algorithm that studies existing fragrance formulas and then compares the ingredients to other data sets, like geography and customer age. This algorithm, which was created in IBM’s Thomas J. Watson Research Center and which the company has named Philyra, can now develop new perfumes that will target very specific market segments.

Whether the IBM systems works or not, the idea may be that algorithms provide a way to emulate a scent and point to the math, not a human “nose” able to duplicate a competitor’s fragrance. I noted this statement:

Applying machine learning to the fragrance industry, for instance, could help companies dupe highly coveted scents without violating trade secrets by using an algorithm to simply tweak the formula slightly.

What’s the fragrance generated by RedHat employees who find that IBM is different from the pre acquisition RedHat?

Spicy, I would wager.

Stephen E Arnold, November 7, 2018


Comments are closed.

  • Archives

  • Recent Posts

  • Meta