Fully automated futures trading

" I have a method for fitting forecast weights that I will probably blog about. It involves fitting on each instrument individually, then clustering and fitting clusters; finally fitting across the whole set of instruments. The final forecast weights will be a blend of the weights from each of the three methods, the blend depending on the amount of data an instrument or cluster. Quite slow to do, I'll probably do it as a single in sample fit once I've tested it, and quite heuristic, but I would like to introduce some more instrument specific weightings where that is justified. I expect this will be in my next blog post."

I expect I was right
https://qoppac.blogspot.com/2021/05/fit-forecast-weights-by-instrument-by.html

GAT
Thank you for all your work, an your extensive blog entry about the results. I am lazy, so I will stick to the handcrafted forecast weighing factors as provided in your first book.
 
An unrelated question: big-tech has been booming lately, and the way that model works, as I understand, is that there are these large venture capital firms in the tech-hubs like Bay Area which finance private startups, 90% of their bets go bust and maybe 1 or 2 unicorns make up for all the losses and more.
So because all of these is private, we retail investors\traders don't have access to it (there maybe some ways but it's not wide spread). So my question is how much are we generally missing out by not having access to this market of initial-stage private companies? I mean in general it's all equity - same asset class as we can all trade on public exchanges, just sort of a different flavor of it "initial-stage private tech equity".
It's just the majority of people only hear the success stories, how someone who invested in twitter on initial stage made 10,000x of his money or something, but of course he also lost 95% of his other bets, so how really lucrative this business is if researched objectively and systematically (were there attempts to research it?), is there anything fundamentally different between tech VCs and regular hedge-funds?
For me it's just curiosity, there's really nothing I can actually do about it either way, except maybe being able to better filter the overhyped news about awesome startup investment successes..
I know for example that investing in the recent IPOs is generally a bad idea, there was research that recent IPOs combined trail the market for the first several years..
There was also some research which concluded that historically every "great new thing" always lags behind the old established industries in terms of actual profits for shareholders (I think they looked at railroads which were very hyped as well at the time)..
 
@globalarbtrader

Hi Rob, really enjoying your journey and insight on here
Slightly off topic but whilst at AHL did any of you guys/gals gain any insight into the workings of RenTechs Medallion fund, other than it being a super levered and active stat-arb machine? (More may be known since i last checked)

Thanks, Steve
 
@globalarbtrader

Hi Rob, really enjoying your journey and insight on here
Slightly off topic but whilst at AHL did any of you guys/gals gain any insight into the workings of RenTechs Medallion fund, other than it being a super levered and active stat-arb machine? (More may be known since i last checked)

Thanks, Steve

Sadly no

GAT
 
Straight to the point, i like it :)

In which order would you advise to read your books for someone aspiring to build something sub $100k capital?

Thanks

Assuming you are interested in trading not investing, read Leveraged Trading first then Systematic Trading.

GAT
 
Hello Rob. A question about the large increase in number of markets traded.
When this is implemented, aren't you afraid that the trading capital allocated to each market will be diluted (severely if a large number of new markets were added), bringing the number of contracts at Forecast 20 down to below the practical number of 4 contracts?
 
Hello Rob. A question about the large increase in number of markets traded.
When this is implemented, aren't you afraid that the trading capital allocated to each market will be diluted (severely if a large number of new markets were added), bringing the number of contracts at Forecast 20 down to below the practical number of 4 contracts?

No because I'm going to introduce a new optimisation layer. Briefly (because more detail will come out later) this will take on the best portfolio of discrete positions, given the capital I have available.

GAT
 
Back
Top