Business Analytics Error: Learn from Uber’s Mistake During the Sydney Terror Attack by RK Paleru.
From the post:
Recently, as a sad day of terror ended in Sydney, a bad case of Uber’s analytical approach to pricing came to light – an “algorithm based price surge.” Uber’s algorithm driven price surge started overcharging people fleeing the Central Business District (CBD) of Sydney following the terror attack.
I’m not sure the algorithm got it wrong. If you asked me to drive into a potential war zone to ferry strangers out, I suspect a higher fee than normal is to be expected.
The real dilemma for Uber is that not all ground transportation has surge price algorithms. When buses, subways, customary taxis, etc. all have surge price algorithms, the price hikes won’t appear to be abnormal.
One of the consequences of an algorithm/data-driven world is that factors known or unknown to you may be driving the price or service. To say it another way, your “expectations” of system behavior may be at odds with how the system will behave.
The inventory algorithm at my local drugstore thought a recent prescription was too unusual to warrant stocking. My drugstore had to order it from a regional warehouse. Just-in-time inventory I think they call it. That was five (5) days ago. That isn’t “just-in-time” for the customer (me) but that isn’t the goal of most cost/pricing algorithms. Particularly when the customer has little choice about the service.
I first saw this in a tweet by Kirk Borne.