What stochastics processes (if any) are used to model currencies exchange rates
and how good are such models ?
References on subj. are also highly welcome.
-
1$\begingroup$ triangle arbitrage is a good start $\endgroup$– pyCthonCommented May 28, 2013 at 1:40
2 Answers
I work extensively with currency models and have to admit there is not much in the public domain regarding recent published research that may satisfy your needs. Some of the below mentioned models incorporate stochastic components but please keep in mind that most research on currencies focuses on fundamentals (such as balance of payments) and depending on your investment and trading horizon they may suit your needs. There is hardly anything published that deals with high frequency currency models that I would deem noteworthy but I am happy to stand corrected by others if they can dig up such research.
Having said that may I point you to some dated papers that may generate ideas and on which you may expand:
Olson is a highly respected data supplier as well as research house (they recently also offer investment services). They provide access to some of their older research: Olson
Another dated paper that walks through some of the more basic methodologies: Link
The following papers provide somewhat of an introduction to modeling fx strategies in higher frequency space though I did not derive much added value out of those. See for yourself whether you like any of those:
I'm not exactly sure what you are looking for but if you're interested in models for longer periods this overview paper might be a good starting point for you. If you can tell use more about what you want to do with the model it might be helpful to give more specific answers.