Search results

How old is your son? GAT

Ignoring the well known issues with these kinds of track records, 12.5K euros over 3.5 years is hardly a success. It's less than 10 euros a day... GAT

Audio Would make a great film. +1 for Helena Bonham Carter as the villain, Dr Ruja GAT

Highly recommend this podcast https://www.bbc.co.uk/programmes/p07nkd84/episodes/downloads May not be accessible for non UK type people. GAT

Don't do this. A) You are using information you didn't have at the start of the backtest. Not sure if confirmation bias is the correct term, but it's definitely bad (I call this implicit fitting). B) It's unlikely the differential in performance is statistically significant or meaningful. Use...

The latter shouldn't do anything... where did you see it? Thanks GAT

Curious about why you feel you have to do this daily. I follow the same approach, but 2-3 times a year. GAT

... was quite credible up until this point. You could argue this is clickbait to get people to sign up to what may be a good course, but still.... Is clearly not true (assuming we can agree on what 'classic' data science is) GAT

Hi Sturm Nice post. I think you can just plug your adjusted sharpe ratio and expected vol into the standard kelly equation so you don't need to do any more calculus if you have a closed form equation for expected SR / vol given some expected unleveraged return / vol / leverage. Of course since...

Not again <slaps forehead>. If I had $1 for every 'can you reverse engineer' post on ET I've seen, I'd have about $22. No, not possible. You can work out someones 'style' from trades (basically beta, factor exposure), but not any alpha they are adding. @Option_Attack is right. GAT

I don't, but one quick way I use to answer this question myself is to buy a nominal amount of a security and see what the haircut is. This gives you an answer T+1 which is usually quicker than IB customer service. GAT

Isn't this just common sense? If you want to get rich from employment you have to do a combination of the following: (i) earn a lot of money, (ii) save a substantial fraction of your income, and (iii) make high investment returns. So if you don't earn a vast salary you are going to need to spend...

Since you didn't like my first response here's another. Generally it's a waste of time to reverse engineer trading strategies, regardless of their source. At best you are going to be able to work out what risk factors they are exposed to. But if they have any genuine alpha then you are unlikely...

It is a good analogy because the quality of trading strategies on C2 (and similar sites) is likely to be very poor. Reasons include: easily gamed poor choice of metrics for leaderboard, incentivising ridiculous levels of leverage likely to be overfitted likely to be produced by people who...

Quick update. My new book is out officially, although annoyingly Amazon US have already sold out (some SNAFU with the order, or I've sold a hell of a lot more copies than the publishers expected to). @kevinkdog has already given me a nice review. Trading wise I'm now in a ~10% drawdown from the...

For younger readers, the Lada was a soviet era motorcar that was a byword for poor quality and general terribleness (apparently they're still made). Nobody from GM or Ford ever felt the need to reverse engineer a Lada. GAT

And as a postscript, the strategies in my books still work and I still use them. Because they trade slowly, are based on sources of return that decay extremely slowly, and highly liquid, it's unlikely they will be competed out of existence any time soon. That doesn't apply to faster strategies...

Fascinating thread. I like and respect both Kevin and Ernie (and Marcos for that matter), so it's a tricky one. Partly I think it depends on what you mean by 'success', what you mean by 'algo trading', and what you mean by 'ML'. These aren't all well defined terms. So I think it's possible for...

Fine with me GAT

Quite right, edited my post. GAT