Live data from Hacker News

COTA: Improving Uber Customer Care with NLP and Machine Learning

eng.uber.com

11–12 of 12 posts

Re: COTA: Improving Uber Customer Care with NLP and Machine Learning

#11
post #5
post #3

Earlier quoted context omitted.

I had the misfortune to be on the receiving end of their stupid AI recently. I posted a ticket saying i was overcharged unfairly for a trip, and a bot resolved the issue and sent a reply apologising for the incovenience and hoping i use uber again soon. I demanded to speak to a human, but got the same automated reply again! Boooooo!

>I demanded to speak to a human, but got the same automated reply again! Why? It's a low margin business and stuff like this drives up cost for everyone. I'd rather have low cost rides than talking to human support

>Why? It's a low margin business and stuff like this drives up cost for everyone. I'd rather have low cost rides than talking to human support

To be picky, it is a negative margin business (at least until now).

Still this is not a reason to have not decent customer support.

The usual approach (not necessarily by Uber, almost everyone is on this - IMHO flawed - track) is the periodical announcement roughly on the lines of "our automated, automagical AI/whatever is so perfect that the service/product was so bettered that the need for support was reduced to 0.0000000000001% of customers". (which is good)

Then, IF it was actually true (it usually isn't) that single request every zillion transactions/sales could be actually dealt with properly with a marginal cost by a human (possibly someone actually capable and with the powers to actually provide some form of remediation).

Re: COTA: Improving Uber Customer Care with NLP and Machine Learning

#12
post #2

Seems like a lot of work to get a supposed 10% agent efficiency gain, and the article is silent on whether this translates to improved customer satisfaction. If anything, it seems like this would further exacerbate the tendency of high-volume scripted support to be unable to deal with anything that's not the common case. Most ML in support implementations I've seen, including the one in my team [1], focus more on pro…

> Then, we measured customer satisfaction scores and compared them across control and treatment groups. In general, we found that customer satisfaction often increased by a few percentage points. This finding indicates that COTA delivers the same or slightly higher quality of customer service.
Post reply on HN