Top all-time · #11866
Zachary David
Personal blog · zacharydavid.comdataeconomics
Zachary David's personal blog at zacharydavid.com covers data and economics. Since 2014, 6 different Hacker News readers have linked it 7 times. The last post was in 2018, but the archive is still widely read.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link Zachary David's posts on applying ML to finance, where one commenter says the article explains the methodology problem well, and on HFT quote stuffing as a software bug.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
What Hacker News says?
When applying CS/ML to finance, methodology is absolutely crucial. Yet most work - even work done by quants in major sell-side banks - pays little attention to methodology; it is often naively assumed that the methodology applied to classifying cat images can be directly transferred into the domain of finance. Here is an article that explains the problem well: http://zacharydavid.com/2017/08/06/fitting-to-noise-or-n…
Comment linking /2017/08/06/fitting-to-noise-or-nothing-at-all-machine-learning-in-markets/
on “Predicting Stock Performance with Natural Language Deep Learning”Submitted Fitting to Noise or Nothing at All: Machine Learning in Markets as a story · 295 points
HN discussionThat's not what's happening here. Traders are arbitraging and reacting to public trades and orders on multiple markets. If you walk through a physical market where 8 apple carts are lined up, all selling apples for $1, buy every apple at cart #1, then buy every apple at cart #2, and so on, would you be surprised to find the price moving up or sellers stepping away as you approached carts #7 and #8? The same thing ha…
Comment linking /bad-research/the-hunsader-follies/
on “A detailed exposé on how the market is rigged from a data-centric approach”Submitted Machine Learning in the Financial Markets as a story · 11 points
HN discussionThemis trading wrote a report saying HFT is evil? This is about as persuasive as the taxi industry releasing a document saying that Uber is worse than Voldemort or the hotel industry saying AirBnB is the devil. Furthermore, many of the issues described there are fairly innocuous in reality. For example, flickering (aka "quote stuffing") is a software bug which costs HFTs money: http://zacharydavid.com/2014/04/on-hft…
Comment linking /2014/04/on-hft-part-ii-bugs-features-and-aggressive-incompetence/
on “Capital Is No Longer Scarce”- po · 2014-05-18
Submitted Technologies of Future Governments and Electorates: Artificial Intelligence as a story · 2 points
HN discussion http://zacharydavid.com/2014/04/on-hft-part-ii-bugs-features... This blog post details similar issues that can lead to rapidly canceled orders. Generally, firms that are smart avoid moving their prices around "too much" since: a.) You lose your spot in the queue. If I am near the front of the price/time queue buying at 100.01 and move to 100.00 and back up again, now I'm behind everyone else and will either lose opp…
Comment linking /2014/04/on-hft-part-ii-bugs-features-and-aggressive-incompetence/
on “HFT Quote Stuffing is a software bug”