Search results

Will check that out Thanks GAT

I've gone for a shadow cost of 2000 which puts the stats at gross 1.35 / net 1.23 / costs 0.12 / turnover 25.5 A net SR of 1.23 isn't the 1.43 or so I thought I'd get, but it's still okay. Costs are slightly higher, but turnover is matched. I think my production costs will be lower anyway...

Shadow cost 500, gross SR 1.47, net SR 1.3, costs 0.17, turnover 43 GAT

A cautionary tale TLDR: I've found an issue in the dynamic optimisation method. It's probably not a massive problem unless you're really pushing it to extremes like me (over 100 instruments with $500K of capital). I plan to update the blog post today with my updated findings (which I'm still...

Probably going to be the most entertaining thread for a while... GAT

Long end of the curve usually moves less as it's barely influenced by current rate policy, except for targeted QE. Hence the curve flattens in a sell off. GAT (According to LinkedIn, expert in fixed income)

It probably doesn't calculate individual correlation but infers the final value from exponentially weighted covariance and variance figures GAT

I think you're a bit confused about how exponential weighting works. We exponential weight the last 5 years, and they will get steadily decreasing weights. Let's take a simple example. Suppose your decay is 0.25 (an extreme example) The weights on each correlation (or whatever we're...

I think you mean 'after so many months'. The micro BTC was only launched in May. GAT

No basically what we do is first take the last 20 years of data, and then calculate the exponential weighting on that 20 years with the appropriate halflife. This first step is basically optional, since the influence of a day of returns twenty years ago will be miniscule given the half life of...

It's a hard one for sure. I've said many times before that excel is fine for running an 'out of the box' trading system, since it's just coding up some rules and then combining them linearly. And I know another guy who is running basically my original system, but on excel. But for backtesting...

Also it's pure python; I could probably make it faster by using a library like CVXPY as suggested a few posts ago (that doesn't implement the greedy algorithim, so not like for like). GAT

It's a fraction of a second for my current use case: 103 instruments with ~$500K of capital on my production machine (32gb/i7 8 threads / 3ghz). I can run a full backtest with 100 instruments in a less than five minutes, so that's approximatly 10,000 optimisations (40 years *250) on my laptop...

There's an awful lot more you have to do to avoid overfitting. GAT

That's very kind, but I can do my own overfitting. I don't need any help thanks GAT

People often compare the growth of crypto to other nascent technologies like the web. BTC was 'founded' in 2009, about 12 years ago. 12 years after the web was 'founded' in 1990 was 2002. I'd bet there were more than 412 retailers with websites in the UK in 2002. Statistics don't go back that...

"2. Digital assets are not accepted in the “real economy.” ... PayPal and Square have added BTC and other digital currencies to their payment networks" From the paypal website "Can I use crypto to pay or send money? For now, you can't currently use crypto to pay or send money on PayPal. "...

Most likely when the optimal position (generated from forecasts) goes to being a different sign to the current position. So if we're long, but then the forecast goes short, we'll close our position. We could also close earlier if the optimal position gets small enough, and the trading costs...

Actually very good, but then markit are a reputable firm not a crypto ponzi supporter. GAT

Er... it doesn't? Why would it do that? GAT