Recent content by wopr

Thanks! I thought about doing that, but was not confident that I didn't mess up something with returns calculations on my side. I just divided the SR by 2 and indeed getting more reasonable results.

I'm about a week in into my adaptation of handcrafting for forecast weights, I think I got it working. For those looking to implement, but are not using pysystemtrade, I've found it to be a sweet spot to hook into optimiseWeightsOverTime...

Is that on your local branch somewhere? Looking at the code, both master and develop branches, I see that when estimating weights, ultimately pandl_for_instrument_forecast() is called, this one...

Rob, I've been working through pysystemtrade code for calculating net returns for optimization, stumbled upon gross returns adjustment for SR costs, here https://github.com/robcarver17/pysystemtrade/blob/ad5c79cdfb99dd337558136b501d6d514549e2cf/sysquant/returns.py#L174 Shouldn't that line...

Hm, in that case I don't really see where the (small) differences in forecast weights for instruments in the same asset class come from. Eg. SP500 and NASDAQ, same asset class, both really cheap to trade, have some different weights.

I've just started the effort of being a bit smarter about my forecast weights, so went back and re-read the handcrafting series and a few other related blog posts. Regarding the above, so if I understood correctly, the differences in forecast weights for instruments within the same asset class...

I've been doing some research into relative momentum as implemented in Rob's latest book. I used my second of 3 copies for this research. Rather than running a backtest, I wanted to see the effect in play. Here's a somewhat complex chart that says a lot (click to see the full image). Basically...

For me, SR is about 10% better for the modified version. That's all after costs, for exact same set of instruments and forecasts. I use Rob's method of having everything in weights. At that point in the process (DO stage), I don't want to have to deal with exchange rates and stuff. So I think...

Hi Luis, thanks for posting! I saw that and actually spent a good week trying to make that work, but I just couldn't figure it out. You defined the problem slightly differently and I couldn't figure out how to replicate it, I think I got confused by the target risk multiplier. Added to that that...

I've been playing with DO implementation, and stumbled upon what could be a slight improvement so wanted to share. I've been trading Rob's implementation of DO for about 2 years now, and I've been noticing that I would sometimes have a position on in an instrument that has optimal unrounded...

I'm debugging something with my DO implementation (gist of the issue is, in my backtesting, performance of the DO drops significanly with lowering the capital, eg. from a 1.14 SR for a Jumbo portfolio to 0.91 SR for DO with 800K, for the same forecasts), I think I narrowed it down to correlation...

I'm not there yet with confidence level. Since I'm typing, small update from me. I've just completed a big effort to add more markets, sort of like what Rob did a year or so ago. I'm at 104 markets right now. Since that will cause some reshuffling in the portfolio, I also used this to add more...

I was checking out your strategy report Rob (https://github.com/robcarver17/reports/blob/master/Strategy_report) and I noticed that you don't trade any trend rules for Bitcoin, any reason for that? Micro contract is quite cheap too. I noticed as I saw you have a short on, and Bitcoin has been on...

Thinking about this some more, why is a bimodal distribution an issue? If we had a bimodal distribution, with peaks at, say, -5 and 5, would that not be ok for our use case here? We could use 2 as the forecast scalar to get the average absolute forecast of ~10. I'm sure I'm missing something here.

Hey Rob, I was doing some digging into various rules and stumbled upon a weird thing. The raw and smoothed forecasts for breakout have interesting distributions. That's for S&P500, 24 years of historical data. I double checked the data and code for the rule, even used your implementation...