People, every show

Amanda Stent

Researcher, Bloomberg. On 1 show, 1 appearance. The Shows tab opens the full record on each.

Amanda Stent is a natural language processing researcher at Bloomberg. She specializes in text analytics and language applications designed for the finance sector.

1shows
1appearances
14statements
5resolved
3supported
1contradicted
60%fully supported

Everything Amanda Stent said on any show that made the record, most notable first. Each card names its show and opens the statement there.

MAD Assertion Supported
Stent: No generic text analytics platform can handle financial language
“There is no on the market generic text analytics platform that can handle this type of language. No way.”
Amanda Stent Mar 2, 2018 ▶ 6:51 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Disclosure
Bloomberg can automatically generate news articles without humans in two minutes
“And this kind of article we can now automatically generate. So you can get this with no human intervention within two minutes, and then within five minutes a human journalist can come along in art color.”
Amanda Stent Mar 2, 2018 ▶ 8:29 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Assertion Partly supported
Generic NLP mistakenly linked Bill O'Reilly news to O'Reilly Auto Parts
“Okay, so Bill O'Reilly said something, and there's a small and innocent company called O'Reilly Auto Parts somewhere in the Midwest, and a bunch of generic text analytics engines linked Bill O'Reilly to O'Reilly Auto Parts, and the O'Reilly Auto Parts stock dr…”
Amanda Stent Mar 2, 2018 ▶ 9:48 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Disclosure
Bloomberg filters social media manipulation using account metadata and supply chain data
“We do a lot of historical monitoring, so we can know how old a social media account is. We also have a very, very large collection of pieces of information about entities in the world, so we can know how closely associated a particular handle is. With a decisi…”
Amanda Stent Mar 2, 2018 ▶ 16:15 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Disclosure
Stent: Bloomberg shifted data labeling to deep learning and decision trees
“And that's something that historically has been done mostly with rule-based systems, but today we do it with deep learning and a lot of decision trees.”
Amanda Stent Mar 2, 2018 ▶ 13:49 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Insight
Stent: Earnings call cues cannot reliably predict financial performance
“So we can't always predict based on the non-linguistic or even the linguistic features of a, of an earnings call or an earnings release.”
Amanda Stent Mar 2, 2018 ▶ 23:13 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Assertion Supported
Stent: One-minute news reporting delay corresponded to 3% stock price move
“The distance between 10 38 and 10 39 Was about three percent in the stock price. The distance between the SEC headline and 1055, 20 minutes later, was a 12% absolute difference in the stock price.”
Amanda Stent Mar 2, 2018 ▶ 3:13 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Assertion Supported
Stent: SEC declared Twitter valid for official corporate disclosures
“SEC has declared that Twitter, in particular, can be used to provide company, official company announcements.”
Amanda Stent Mar 2, 2018 ▶ 3:38 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Insight
Stent: Vertical NLP faces key hurdles in domain language, speed, and precision
“Here are three key challenges that we face that would be present to a greater or lesser extent in any other highly highly vertical industry. The first is financial language, idiomatic language. The second is the need for speed. Remember, I said a minute. And t…”
Amanda Stent Mar 2, 2018 ▶ 5:41 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Assertion Not checkable as stated
Bloomberg NLP models feed over 100 Bloomberg Terminal screens
“And they feed over a hundred different screens within the Bloomberg terminal, which provide company trend information, company tweet information, sentiment information, sentiment alerts, tweets on mergers, tweets by the president of the United States, et ceter…”
Amanda Stent Mar 2, 2018 ▶ 9:17 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Disclosure
Stent: Bloomberg Terminal contains between 15,000 and 40,000 functions
“There are, nobody has told me the actual number. I've heard numbers from between 15 and 40,000 individual functions inside the Bloomberg. Each of them is fed by at least one data feed, and in many cases, several.”
Amanda Stent Mar 2, 2018 ▶ 14:12 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Opinion
Stent: Bloomberg's human-written stories are much more informative than automated ones
“Our manually generated stories, which are frankly much more informative”
Amanda Stent Mar 2, 2018 ▶ 21:12 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Assertion Contradicted
Stent: Bloomberg sentiment feed outputs probabilistic buy or sell signals
“So the Bloomberg sentiment feed is not just positive or negative. I like it right. It's buy or sell, and it's with probability so that you can use those in your own models.”
Amanda Stent Mar 2, 2018 ▶ 23:30 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)
MAD Disclosure
Stent: Bloomberg NLP aims to inform trading decisions, not track sentiment
“At Bloomberg, we're not trying to identify net promoter score. We're trying to really understand what's going on so that someone else can decide whether they should buy or sell this company.”
Amanda Stent Mar 2, 2018 ▶ 5:31 Text Analytics for Finance // Amanda Stent, Bloomberg (FirstMark's Data Driven)

One line per show, most statements first. The link opens Amanda's full record on that show: the calibration, argument clarity, speaking style and every statement made there.

ShowRole thereEpsStatementsRecord
MADLEDGER Researcher, Bloomberg 1 14 60% 3/5 full record on the MAD Podcast →
Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.