The recent move by the Swiss National Bank (SNB) to remove the peg between the Swiss Franc and the Euro has caused lots of turmoil (see here and here) in an already volatile environment. The magnitude of the event was a pure surprise to me. Yes, this is Switzerland, and this is the Swiss Franc, but, from a mere technical point of view, after the peg in September 2011, the Franc should not have been treated any more as a major currency. Consider, which currencies are pegged? If China removes the peg between the Yuan and the US dollar, would it send the same shock waves through the world markets? I doubt it.
It’s embarrassing, but hoping it might be useful to others, I’ll share it anyways.
At the beginning of January, as usual, I posted the allocations for that month for the strategy I call Max-Sharpe and which I try to follow. So what’s the deal? Well, I wasn’t able to enter these positions, since I became too “greedy”.
Today over a coffee, me and a friend did a quick analysis on the Russell 2000. The reason was that I was holding a short, and was debating whether to close it or not. Not only the outcome of this analysis made my action clear, but it also surprised me quite a bit. Here are the monthly statistics for the month of December.
In an earlier post, I used mclapply to kick off parallel R processes and to demonstrate inter-process synchronization via the flock package. Although I have been using this approach to parallelism for a few years now, I admit, it has certain important disadvantages. It works only on a single machine, and also, it doesn’t work on Windows.
It has been a while since my system had a position in the S&P 500, but it’s back. Went long at the close today.
December is going to be interesting, mostly from a performance point of view. Based on seasonality, emotions and gut feeling, I’d go mostly into stocks, mostly US. My Max-Sharpe approach tells me otherwise, and I will stick with the boss’s allocations. Here they are:
Have you tried synchronizing R processes? I did and it wasn’t straightforward. In fact, I ended up creating a new package – flock.
One of the improvements I did not too long ago to my R back-testing infrastructure was to start using a database to store the results. This way I can compute all interesting models (see the “ARMA Models for Trading” series for an example) once and store the relevant information (mean forecast, variance forecast, AIC, etc) into the database. Then, I can test whatever I want without further heavy lifting.