Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Jane Street Market Prediction ($100k Kaggle competition)

kaggle.com

Post reply on HN
Print view View original

71–80 of 217 posts

Re: Jane Street Market Prediction ($100k Kaggle competition)

#71

Post by ciamac »

fractionalhare wrote: post #58
rahimnathwani wrote: post #55

Earlier quoted context omitted.

"have no domain expertise in the underlying data. This kind of approach to finance has historically performed poorly" I recently read 'The man who solved the market', about Jim Simons and Renaissance Capital. The way the book tells it, looking for patterns without seeking domain expertise (e.g. ignoring fundamental valuation of equities) is exactly what Renaissance did, and it worked out very well.

I can see why someone would characterize RenTech that way but it's not really fair to do so. There is a lot of mythos about how Simons hired computer scientists, mathematicians, signal processing and NLP experts, etc. When Mercer came over from IBM, he definitely contributed a significant amount of analytical expertise that was probably nonexistent in financial trading at the time (with the possible exception of the…

That DB/rentech basket option is a tax avoidance scheme. It has nothing to do options pricing and concepts like delta, gamma, etc.

Re: Jane Street Market Prediction ($100k Kaggle competition)

#72

Post by 2-tpg »

paxys wrote: post #59
toomuchtodo wrote: post #2

Any model superior to what Jane Street is running is worth vastly more than the prizes they’re offering. If you prove such a model out, get licensed (SEC, FINRA) and start soliciting to manage assets. Disclaimer: Not investment advice. Not a lawyer, not your fiduciary.

Why do you think this competition will result in a model superior to what Jane Street is running?

The winner model will likely outperform anything that Jane Street could come up with this 130 feature set. With 3000+ competitors, the top 10 will likely be superior to what Jane Street can do in-house. Then an ensemble of the top solutions will be the best possible model anyone can come up with.

Re: Jane Street Market Prediction ($100k Kaggle competition)

#73

Post by 2-tpg »

basicneo wrote: post #42

By a similar argument to https://danluu.com/sounds-easy/ , no one will beat Jane Street in a weekend. Jane Street's hiring standards exceeds FAANG's. This is a hiring/branding strategy. Good luck to them.

I actually give it 48 hours before the top 3 equals what Jane Street can do in-house on this exact same dataset. A week before the reasonable plateau is reached, and a month or so before the absolute most information is squeezed out.

Re: Jane Street Market Prediction ($100k Kaggle competition)

#74

Post by fractionalhare »

ciamac wrote: post #71
fractionalhare wrote: post #58

Earlier quoted context omitted.

I can see why someone would characterize RenTech that way but it's not really fair to do so. There is a lot of mythos about how Simons hired computer scientists, mathematicians, signal processing and NLP experts, etc. When Mercer came over from IBM, he definitely contributed a significant amount of analytical expertise that was probably nonexistent in financial trading at the time (with the possible exception of the…

That DB/rentech basket option is a tax avoidance scheme. It has nothing to do options pricing and concepts like delta, gamma, etc.

Yeah, yeah. That controversy has been litigated on HN a dozen times already, I'm not going to rehash it. Do you dispute my primary point here? If so, why?

(Also, even if I agree it was purely intended for tax avoidance, I don't understand why you think that would obviate having to understand how the options work intimately well).

Re: Jane Street Market Prediction ($100k Kaggle competition)

#75

Post by Traster »

2-tpg wrote: post #69
1helloworld1 wrote: post #38

Isn't it pretty well known in the finance world that using stale public information to predict the market is a fool's errand? Unless you have some kind of specialized non-public data (e.g satellite images of number of cars parked outside parking malls, number of cargo ships moving in and out), trying to predict the market with historical data does worse than "Just give me some monkeys, darts and a dart board".

Using purely historical price data it is harrowingly difficult. There are 130 anonymized features, so that's unlikely to be only price data. It could include information on the order book, correlated assets, fundamentals, vectorized/embedded text, etc. Besides, I bet you can train monkeys to do (slightly) better than blindfolded random throwing. Even with public data (replace satellite images with Youtube mentions, o…

One thing we need to be clear about is that you're not aiming to be better than average. You're aiming to make a profit. There are probably hundreds of thousands of day traders, there are probably <100 market makers and tradingfirms (far less than that for a some specific products) and you'll probably find 99% of the day traders aren't making systematic profits. There are lots of strategies that are much better than average and still worse than putting your cash in a bank.

Re: Jane Street Market Prediction ($100k Kaggle competition)

#76

Post by riazrizvi »

georgeecollins wrote: post #63
riazrizvi wrote: post #51

Earlier quoted context omitted.

Mathematical analysis of financial markets is more celebrated when applied to relative valuation of different assets, rather than prediction of the market. Black-scholes, for example, applied calculus with an underlying no-arbitrage assumption to create a thriving market in option pricing, by giving traders a mechanism to reduce risk and thereby reduce bid offer spreads. Same in fixed income, mortgage, and credit mar…

This! >> The problem with predicting absolute levels, is that there is a game theoretic aspect which undermines any mathematical trading strategy as soon as it is public. I took finance in Business school, coming from doing a lot of statistical analysis in a research lab. I hated my finance professors and there pseudo science. Pricing formulas work great until they don't. The problem is when they don't, they really d…

To clarify, the hedge fund LTCM in "When Genius Failed", collapsed not because it relied on arbitrage 'pricing formulae', rather because it failed to properly execute arbitrage trades.

LTCM in being overly leveraged, relied on other market participants to maintain short term price alignment, which meant it was not arbitrage. Salomon's reduced its role as market-maker, maintaining short term price alignment, which increased short term price anomalies, and thus increased LTCM's vulnerability. The Asian financial crisis increased the frequency and extent of those pricing anomalies, and the subsequent Russian Default crisis did the same. Margin calls were made on LTCM that it couldn't cover, forcing them to close out of their positions at very unprofitable times of the trade strategy.

So I don't think "pseudo-science" is a great description for what those B-School profs are teaching. Rather the pricing formulae are just the beginnings of the financial theory you need to run arbitrage strategies, but they are not sufficient. You need to augment them with a broader picture of market dynamics and capital management, just like you'd need to learn about financial law, financial market technology, and a bunch of other stuff to run a successful market-making desk.

Re: Jane Street Market Prediction ($100k Kaggle competition)

#77

Post by riazrizvi »

blovescoffee wrote: post #70
riazrizvi wrote: post #51

Earlier quoted context omitted.

Mathematical analysis of financial markets is more celebrated when applied to relative valuation of different assets, rather than prediction of the market. Black-scholes, for example, applied calculus with an underlying no-arbitrage assumption to create a thriving market in option pricing, by giving traders a mechanism to reduce risk and thereby reduce bid offer spreads. Same in fixed income, mortgage, and credit mar…

I've wanted to start learning about this for a while but I'm really not sure where to start. I have a degree in CS and Math so I'm not a total layman wrt the maths. Do you have any suggestions?

What's your goal?

Re: Jane Street Market Prediction ($100k Kaggle competition)

#78

Post by 2-tpg »

Traster wrote: post #75
2-tpg wrote: post #69

Earlier quoted context omitted.

Using purely historical price data it is harrowingly difficult. There are 130 anonymized features, so that's unlikely to be only price data. It could include information on the order book, correlated assets, fundamentals, vectorized/embedded text, etc. Besides, I bet you can train monkeys to do (slightly) better than blindfolded random throwing. Even with public data (replace satellite images with Youtube mentions, o…

One thing we need to be clear about is that you're not aiming to be better than average. You're aiming to make a profit. There are probably hundreds of thousands of day traders, there are probably <100 market makers and tradingfirms (far less than that for a some specific products) and you'll probably find 99% of the day traders aren't making systematic profits. There are lots of strategies that are much better than…

You can aim for both. If you just aim for profit, then you can get lucky with just average, or even random, betting. If you find a weighted coinflip (which is not impossible), provided by how many times you can flip that coin, you will see steady systematic profits. Of course, majority of day traders are getting owned by the big players, and they would do better doing more reasoned and long-term investments. Most day traders are not even using predictive models though.

Re: Jane Street Market Prediction ($100k Kaggle competition)

#80

Post by blhack »

1helloworld1 wrote: post #38

Isn't it pretty well known in the finance world that using stale public information to predict the market is a fool's errand? Unless you have some kind of specialized non-public data (e.g satellite images of number of cars parked outside parking malls, number of cargo ships moving in and out), trying to predict the market with historical data does worse than "Just give me some monkeys, darts and a dart board".

>Unless you have some kind of specialized non-public data (e.g satellite images of number of cars parked outside parking malls, number of cargo ships moving in and out)

Planet labs will sell you all of that data, in case people reading along here are curious.

Post reply on HN