Forums  > Basics  > ANN for learning curve dynamics  
     
Page 1 of 1
Display using:  

Strange


Total Posts: 1681
Joined: Jun 2004
 
Posted: 2019-11-19 03:26
Consistent with the prevailing weather, there is a paper Learning Curve Dynamics with Artificial Neural Networks by Alexei Kondratyev. I don't know much about ANN (or any ML beyond simple linear regressions), but it appears that this methodology can (a) fit historical data that does not necessarily follow normal distribution and (b) potentially add other features into the model.

Has anyone tried to reproduce the results in this paper? Is there an easy way I can play with my datasets and ANN?

PS. given the little I know of ANN, there got to be huge potentially for overfitting the data

'Progress just means bad things happen faster.’

ronin


Total Posts: 685
Joined: May 2006
 
Posted: 2019-11-19 11:22
On quick reading, the model is:

Given the levels of all points on the curve and the move of one point on the curve, each point on the curve either ticks up, ticks down or stays the same. Regress on historical data.

So if one point moves up, presumably neighbouring points will move up by a siilar amount, and points further away less so. All capped and floored to plus minus one tick. PCA capped and floored, in other words.

The ANN angle looks a little bit contrived to me.

"There is a SIX am?" -- Arthur

nikol


Total Posts: 1385
Joined: Jun 2005
 
Posted: 2019-11-19 13:56
For very quick start

https://machinelearningmastery.com/introduction-python-deep-learning-library-tensorflow/

Disclaimer: the site helps with quick start, but at some deeper points you might encounter "lose ends" or simply wrong statements there.

There are many examples in github.

At some point I switched to keras.tensorflow on CUDA. Really fast. But all-in-all it is perhaps better to rent one of those AI-clouds with pre-installation.

Today, Google's Tensorflow is most famous, however, yesterday I read some stats that 70% of all publications of 2019 use PyTorch (dev by FB).

To overcome overfitting problem you could use blend of models to MC-generate training sample and then use "transfer learning" techniques (no single recipe) to train on smaller and real sample. It is sort of "deep learning".

ANN is good to use when you want to reduce operational hurdle, not to improve your knowledge about things (there are some exceptions though).

Example: imagine, you calibrated data with model-A, but tomorrow it stops working and you substitute it with model-B. It takes time to: identify that something is wrong, search for replacement, implement/test/put into production. With ANN basically there is no transition, you just incrementally train (transition learning) your model such that it adopts new reality.

PS. ANN does not "understand" the problem. It just fits into it and you don't know exactly why... It involves a lot of intuition, but it grows with experience.

... What is a man
If his chief good and market of his time
Be but to sleep and feed? (c)

Strange


Total Posts: 1681
Joined: Jun 2004
 
Posted: 2019-11-19 14:23
Just heard a podcast with the guy, not sure what to make of it. His main claim is that "it matches non-gaussian dynamics better than PCA", though I still don't understand how do you back out a fair curve give the current set of points.

@nicol, thanks - i will try playing with it for a little bit

'Progress just means bad things happen faster.’

nikol


Total Posts: 1385
Joined: Jun 2005
 
Posted: 2019-11-19 14:44
for fun:
https://antoinesavine.com/2019/11/01/deep-learning-derivatives-pricing/

In principle, one don't need ANN to do this trick - apply integrated sigmoid to option prices as function of strikes. That's one function. If you apply many nodes (~ANN layer) the fit will become better. Same as increase of polynomial degree.

... What is a man
If his chief good and market of his time
Be but to sleep and feed? (c)

tabris


Total Posts: 1286
Joined: Feb 2005
 
Posted: 2019-11-20 23:43
I am skeptical. Basically, at lower frequencies, the non gaussian dynamics would be too noisy to render ANN useful for 1 step ahead forecasting and at higher frequencies, the linearity should make PCA a better and simpler choice. Agree with others on this that ANN for this problem just sounds a bit gimmicky. There are possibly/arguably better techniques to achieve what the paper wanted to do out there now.

Dilbert: Why does it seem as though I am the only honest guy on earth? Dogbert: Your type tends not to reproduce.

mtsm


Total Posts: 255
Joined: Dec 2010
 
Posted: 2019-11-22 21:26
Some people from a Eurozone bank mentioned to me that they could not really reproduce that stuff. Not sure how hard they tried. They are a trustworthy crowd though, in the weeds of this stuff.

nikol


Total Posts: 1385
Joined: Jun 2005
 
Posted: 2019-11-22 22:03
Short recipes:

- Normalization and input/output transformations are the key. What happens inside is a bit of enigma (not completely of course).
- Start with some very simple network architecture and then make it more complex.
- Gradual increase of complexity is even possible (it is part of learning transfer techniques). This can save overall training time.
- All modern ANN libraries allow intermediate saving of the model (net topology + node weights), use it and keep track of nodes changes, not only output residuals (or whatever metrics in use).

I like this visualization demo. Simple but effective learning kit.

https://playground.tensorflow.org/

... What is a man
If his chief good and market of his time
Be but to sleep and feed? (c)

nikol


Total Posts: 1385
Joined: Jun 2005
 
Posted: 2019-12-04 07:13
https://www.risk.net/awards/7216346/rising-star-in-quant-finance-blanka-horvath-aitor-muguruza-and-mehdi-tomas

... What is a man
If his chief good and market of his time
Be but to sleep and feed? (c)

jiuer7844


Total Posts: 11
Joined: Oct 2021
 
Posted: 2021-10-01 03:04
Travis Scott Jordan 1

Yeezy Shoes

Yeezy Supply

Air Jordans

Jordan 11s

Jordan 11

Jordans Shoes

Retro Jordans

Moncler Jackets

Nike Air Jordan

Moncler Outlet

Off-White

Yeezy 450

Yeezy 500

Yeezy

Yeezy 700

Yeezy Supply

Off White Shoes

NFL Jerseys

Jordan Shoes

Jordans Shoes

Yeezy 350 V2

Adidas Yeezy

Yeezy

Yeezy 700

Yeezy

Nike Outlet

Yeezy Shoes

UNC Jordan 1

Jordan 13

Jordan AJ 1

Yeezy Foam Runner

Nike Outlet

Nike Outlet

AJ1

Yeezy Supply

Yeezy Zebra

Jordan 1 Low

Air Jordans

Pandora Charms

Adidas UK

Nike Store

Adidas Yeezy Official Website

Yeezy 350

Jordan 1

Nike Outlet

YEEZY SUPPLY

Pandora Charms

Nike Shoes

Nike Outlet

Pandora Outlet

Jordan Shoes

Air Jordan 4

Pandora Jewelry

Pandora Rings

Pandora Bracelets

Adidas Yeezy

Yeezy

Pandora Charms

Nike Outlet

Adidas Yeezy

Air Max 720

Nike Air Max 270

Air Jordan 11

Air Force 1

Air Jordan 1

Nike Jordans

Jordan 1s

Pandora UK

Nike Jordan 1

Jordan 1

Yeezy Slides

Nike Air VaporMax

Nike Vapormax Flyknit

Air Jordan 1 Mid

Adidas yeezy

Yeezy Shoes

Adidas Yeezy

Yeezy 350

Nike Shoes

Nike Outlet

Yeezy

NFL Shop Official Online Store

Nike UK

Yeezy

Yeezy 350

https://www.yeezyyeezy.com/ Yeezy https://www.yeezys-700.com/ Yeezy 700 https://www.yeezys-supply.com/ Yeezy Supply https://www.offwhiteshoess.com/ Off White Shoes https://www.nflsjerseys.us.com/ NFL Jerseys
Previous Thread :: Next Thread 
Page 1 of 1