I don't believe a calculation like that would take months. The most complicated computation would be inverting a covariance matrix. And your covariance matrix would only be as large as the number of assets you're trading. The second most complicated computation would be calculating the average single-period return of a strategy, and I don't think anybody can be convinced that this would take months to calculate either.
Either way, the kelly fraction *depends* on a) expected return, b) the variance of that expected return, and c) the correlations between the return and any other things you may be trading. Meaning, the kelly fraction of an asset would change if any one of these three things changed. So, I'm not too clear on where 0.005 would be considered a good number. In context to what? An asset in a portfolio with 5 other differently-correlated assets? What betting period? 1min? 1 day? A month? A kelly fraction of 0.005 is terrible if your period is a month, but awesome if you're talking about a single asset over 1min. And even if you had perfect information that implied infinite leverage, an automated trading system would *still* need to know what your bankroll was in order to place the appropriate bet "automatically" using the leverage limits set by IB. If there aren't any plans to put this functionality in, would you guys be opposed to reviewing code that enabled this feature? On Sep 26, 1:51 am, Lawrence Perepolkin <[email protected]> wrote: > Another point one can raise when calculating a Kelly position size is > that how well a given strategy works. For example, one can optimize an > EMA crossover system that never looses on one particular instrument. If > the system never looses then the Kelly position size would be infinity > -- a sure thing. Easy to do, using large EMA time frames. Most know that > the chances of winning are small. This type of approach is not that great. > > Another approach would be to use a very large data set -- multiple > instruments with a lot of history -- something that would require a few > months of running 24/7 to crunch out a Kelly number. Turns out a > realistic Kelly number is about 0.005. The turtles have also confirmed > that 0.005 is a pretty good number. Using small data sets one runs the > risk of over fitting. On the other hand, using large data sets one also > runs into the problem of combinatorial explosions--too many parameters > and strategies to evaluate. > > On 09/25/2012 03:18 PM, nonlinear wrote: > > > > > > > > > You are right in that the Kelly Criterion is typically used to > > calculate the optimum bet site (or in the case of trading, the > > position size). However, in JBT it's used for a different purpose, > > which is ranking the strategy with respect to a given set of > > parameters. Think of it this way: suppose you have two strategies, A > > and B. Let's say they make the same profit, and have the same max > > drawdown. What's different is that the Kelly for strategy A is 30, and > > for strategy B it is 60. Which one would you trade? The answer is > > obvious: you want to trade strategy B, because the higher Kelly > > indicates that the performance is more stable and predictable. In JBT, > > the optimizer can be configured to use Kelly as a way to rank the > > optimization parameters. So, Kelly in JBT is used as a strategy > > performance metric (along with other metrics, such as Net Profit, > > Profit Factor) during the strategy optimization. > > > On Tuesday, September 25, 2012 10:58:43 AM UTC-4, B wrote: > > > Hi I noticed that the kelly fraction is calculated. > > > But, I can't seem to find the code in JBooktrader that returns any > > account information in order to use the kelly fraction to size my > > positions. > > > Does that code exist? > > And if not, what's the point then of calculating the kelly fraction? > > > -- > > You received this message because you are subscribed to the Google > > Groups "JBookTrader" group. > > To view this discussion on the web visit > >https://groups.google.com/d/msg/jbooktrader/-/5d2XPjWraH0J. > > To post to this group, send email to [email protected]. > > To unsubscribe from this group, send email to > > [email protected]. > > For more options, visit this group at > >http://groups.google.com/group/jbooktrader?hl=en. -- You received this message because you are subscribed to the Google Groups "JBookTrader" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/jbooktrader?hl=en.
