amuguruza / nn-stochvol-calibrations Goto Github PK
View Code? Open in Web Editor NEWWe implement the paper: Deep Learning Volatility
License: MIT License
We implement the paper: Deep Learning Volatility
License: MIT License
I suggest adding topics such as finance
, stochastic-volatility
, volatility
, options
in the About section at https://github.com/amuguruza/NN-StochVol-Calibrations
In the paper, Deep volatility, my understanding is that the parameters are done with max-min scaling with thresholds, then the vol surfaces are normalized. Is this right? In the notebook, it seems that both xx,yy are first normalized, then xx is normalized again. Then the unnormalized yy data is scaled for max-mins i believe that are supposed to be for the parameters. I love the idea am trying to build my own model off it. Since I'll obviously need to apply the same scaling to my own data it's important I make sure I'm doing it correctly. Thanks!
It would be very useful for the community to see how you calibrated the model to SPX. Did you need to interpolate the strikes and times to fit the model grid, etc. If so, how it was done.
Please consider posting as it is an impressive contribution in and of itself.
Thanks!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.