Show HN: A high-performance TensorFlow library for quantitative finance

https://github.com/google/tf-quant-finance

by partingshots • 6 years ago

153 38 6 years ago

dvt• 6 years ago

Is there any actual value in doing quantitative finance via TF as opposed to just Pandas? I get that calculating a zillion option prices on a GPU is faster, but does anyone actually do that? Not to mention that dataframes (both conceptually, and in practice) seem much more mature and easier to grok than tensors.

cliftonk• 6 years ago

Agreed this is less convenient than pandas for many tasks, however large market makers (citadel securities, Susquehanna, Jane st, Hudson River trading) employ abstractions like this out of necessity.

jabberwcky• 6 years ago

but does anyone actually do that?

Backtesting a regular single symbol model on CPU is often not cheap, especially at higher frequencies. Now multiply that by 50 correlated instruments, each having say, 1500-3000 strikes+sides+expiries in their respective option markets, and the value of GPU offload should become obvious. Backtesting dispersion trades on the S&P 500 using just 5 strikes per underlying, or any other scenario where the evolution of the volatility surface is important would already potentially involve >25,000 individual option markets

All professionals backtest, often numerous times per day

adament2• 6 years ago

If you are pricing and risk-managing complex derivatives books then Pandas is not the right tool for the job. Pandas does not include derivatives pricing models, daycount conventions, schedule generation and algorithmic differentiation which are all basic ingredients in a modern derivatives pricing framework. In general what you are concerned with here is computing the fair value of each instrument usually as an expectation in a simulation or as a solution to a partial differential equation, and the first derivatives and sometimes second-order derivatives of the fair value with respect to the model parameters. Pandas makes a lot of work in empirical finance nicer, data cleaning, time series work, etc. But when pricing and risk-managing a derivatives book as a market maker you are less concerned with inferring the future from the past, and more with interpolating current data in such a way that you do not open yourself to arbitrage.

I worked as a model quant for a year a couple of years ago in a bank in the team responsible for developing and implementing the derivatives pricing models. Everything was written in (a lot of) C++, but I suspected and still suspect that you could get the same performance by leveraging one of the off-the-shelf deep learning libraries with a lot less code. Maybe you would have to write a few central components in C++ and assembly to get the exact same performance. I am glad to see someone actually following through on that idea.

mynegation• 6 years ago

I get that calculating a zillion option prices on a GPU is faster, but does anyone actually do that?

Yes.

Counterparty credit risk calculations are done as Monte Carlo simulations far into the future and on multiple scenarios on top of the baseline. It easily grows to 10^8 times of the number of valuations in the baseline scenario at present time (which itself can be millions of positions).

jsinai• 6 years ago

More likely production systems will be written in C++ than Python.

chewbaxxa• 6 years ago

They’re completely different tools. Tensorflow is a specialised matrix math library. Pandas is just for sql-like data handling.

reallymental• 6 years ago

I understand that this is google's library, and they're promoting TensorFlow's usage, and subsequently the usage of TPU's.

But this can just as easily be done in Pytorch right? Yes we can't have GPU's there but having your model train 50% slower (exaggeration) is better than having to spend 150% of the time taken in Pytorch to debug anything in TensorFlow.

I may be beating a dead horse here, but why doesn't google just accept that TensorFlow needs to be redesigned for more ease of use?

Can anyone point out the benefits of TensorFlow over Pytorch (besides TPU's) ? It's been a few years since I've used TF and I may have missed something.

atty• 6 years ago

Have you used TF 2.0? It’s definitely better in terms of ease of use. Still not as good as Pytorch, in my opinion. Pytorch is still just more... ergonomic, I would say.

However, I don’t think the Pytorch ecosystem really matches tensorflow yet for production, with TFX and all the other nice-to-haves that google and others have open sourced.

As someone who spends a lot of their time doing POCs and research work, I strongly prefer Pytorch. But I have colleagues who mainly productionize language models, and they all seem to like Tensorflow. I don’t know if that’s just inertia on their part, or the result of a considered choice however.

ipsum2• 6 years ago

TFX/TensorFlow Serving doesn't have a PyTorch equivalent. TF has better mobile mobile support. Jax also works on TPUs and is closer (with other libraries on top like Haiku) to PyTorch.

But framework wars are like language wars :) There's probably not too much productive arguments that haven't been made

akhilcacharya• 6 years ago

Appears to be the result of an Area120 incubated project: https://avera.area120.com/

sandGorgon• 6 years ago

I wonder why they are not using the in-built numpy api - https://www.tensorflow.org/guide/tf_numpy

This will be accelerated by Tensorflow - which means acceleration on Macbook M1 as well

proverbialbunny4• 6 years ago

Is this using floating point numbers under the hood? There is a lot you can do with floating point, but for some of what I've worked on you really do want fixed precision types.

pimbrah• 6 years ago

you want fixed point for accounting, but there's no reason not to use floating point in quantitative analysis

bfrink3• 6 years ago

This is a common misapprehension. Yes, fixed precision is great for accounting (like your bank statement) but when you're making a predictive model of asset prices (or higher moments of price distributions) being off by 1 in 10^14 is not important (because your model isn't that precise anyway!) and the performance you get from dedicated floating part hardware is well worth the "loss" of precision.

This wholesale dismissal of floating point for "financial" systems ignores the real business needs which might point you toward fixed or floating point numbers. Always ask yourself - do you need to know this number to better than 1 in 10^14? Are you going to find its square root at some point? Also remember that storing fixed point numbers usually takes more bytes than double-precision floats.

proverbialbunny4• 6 years ago

Always ask yourself - do you need to know this number to better than 1 in 10^14?

Yes, because over time thousands of multiplies and divides means you will get more than a penny off. The more high frequency the more floats become a problem.

leoplct• 6 years ago

Are still someone using Black-Scholes for option pricing nowadays?

adament2• 6 years ago

Yes but it is used as a function for transforming vanilla option prices into a more natural unit: their implied volatility rather than their dollar price. Option traders think of option prices in terms of the implied volatility not the dollar price of an option. So in that sense Black-Scholes is used in the pricing of almost all vanilla options on stock-like things. Even though the price from a market maker usually comes out of a more complex model that (attempts to) ensures the quoted prices are free of arbitrage in the cross-section of strikes and across maturities. Usually some form of either stochastic volatility, local volity or LSV(local stochastic volatility) model.

neolog• 6 years ago

Was this developed for Google internal finance projects?

pantsforbirds• 6 years ago

I was wondering if it was developed to help promote TF more to finance firms.

person_of_color2• 6 years ago

Why would Google employees be doing quant finance on company time?

tazjin• 6 years ago

This is made by a project in Google's internal incubator: https://avera.area120.com/

(I work for Alphabet but have nothing to do with this)

monkeydust• 6 years ago

interesting - have noticed google knocking on my door much more (I am in capital markets) - they have hired of the street so that provides some credibility when mixed in with their strong tech teams. Have interesting debates with my head quant about quant vs automl - what's 'better' :)

person_of_color2• 6 years ago

Are they trying to spin off a hedge fund?

wtf.

pvitz2• 6 years ago

Right now, it looks like a fun project of students who got their hands on Andersen/Piterbarg, Brigo/Mercurio and the QMC part of Glasserman. I wonder what their real goal is with this.

olalonde• 6 years ago

I am not sure if that was meant as criticism but if so, could you be more specific for those of us who are not familiar with the domain?

andyxor• 6 years ago

This was not done by people who make their living in markets

JustFinishedBSG• 6 years ago

I wonder what their real goal is with this.

Google do shadow banking. They are "contracted" by Lloyds, but it's all Google on the backend, developing a Revolut alternative among other things

secondcoming• 6 years ago

We tried to use Tensorflow's native C++ library to run some predictive model in real time on CPU-only. The performance sucked, even though the model was not particularly complex.

My advice would be to only use Tensorflow with the python wrappers. It's just too complex.

vmception• 6 years ago

Hi, I have a need to know the price of Liquidity Pool shares without relying on many oracles and multiple ABI calls

Liquidity pool shares are asset backed by at least two other assets

Can Tensorflow help me with keeping pricing?

Show HN: A high-performance TensorFlow library for quantitative finance

Related Stories