Dear QuantLib Users,
First, I would like to apologize if the following has already been implemented, or if the idea is stupid, as I may have acted before I thoroughly went through the documents and background knowledge.
Anyhow, I would like to propose the addition of Pattern Recognition algorithms to the library. I am not sure how well or how useful they will be to quants, but classification, clustering , kernel algorithms and AI, may be of some use in financial risk assessment. Time-series can also be analyzed with these algorithms by using t-n to t data points to predict t+1. I know it deviated from the books and courses (stochastic processes, curve fitting), but I would just like to know whether the idea is plausible.
Please comment with ideas and critiques.
Thank you,
Pawit Khid-arn
-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://sourceforge.net/services/buy/index.php_______________________________________________
QuantLib-users mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/quantlib-users
Locked
