Search results

Assuming it's allowed you would do exactly that, since it creates a pure arbitrage (which as you approach it Kelly would tell you to be arbitrarily big). That of course gets to the point that Kelly tells you how much to risk, but says nothing about actually having the cash in hand to place the...

Although other folks, like retail FX, have a much better sample.

I can't fathom how this could happen...

Of course you could also do the same with access to a pool of consistently losing traders...

I think we're assuming A and B are independent or very close. That said, I conceptually disagree with your statement. The bets on A and B should be sized the same, but B is MUCH more valuable to dedicate a slice of your portfolio to - to the point that you might never take an A bet for fear of...

It was a pretty limited "trend" though in the sense that it was driven by a desire to take out a big batch of stops (and the offer pulling to make that happen), not underlying liquidity-consuming order flow. I guess it's a philosophical question as to whether anything driven by stop hunting can...

Well, if you really need the EMH disproved in general, go look at the Shiller PE data. It shows pretty clearly that future equities performance is a function of current price - ie. that the price series is NOT some independent random walk. Similarly, look at the Case Shiller index on housing -...

Then get the hell off ET, buy 13 weeks, and don't worry about it. Of course, most markets are woefully inefficient and this is well documented in numerous places, so you'd be dead wrong. But at least you'd be wrong and have your time back which is of no small value.

If I followed your notation correctly, that would be the per-bet risk-sized return on bankroll for the strategy, which IMO is a very good figure of merit and would have to be the basis for anything better. What might be better: - Some additional indication of how many opportunities of said...

Not a compelling argument. "Failing" is only relevant to the degree that something of value is being measured. Given how the combines work, that's VERY debatable. The only thing that isn't debatable about the whole deal is that a very questionable firm will be paid for providing a service...

If you're not planning to use TST for funding, you can get the exact same result by funding an account to get platform access and then trading in simulation. Even with modest data fees that would be FAR cheaper.

The two aren't mutually exclusive - they can have a system that selects unprofitable traders on random luck AND kicks out profitable traders due to unreasonable requirements. Looking at the numbers for the combines, both probably happen with fairly high probability.

It's based on monte carlo equity curves with various kelly fraction bets. 1/5 to 1/10 was the range where they started looking "acceptable" to my eye - no stomach churning drawdowns. Most of the stuff I do has discrete outcomes, so I use discrete Kelly (or the general log/maximization form...

Here's an amusing thing I found: if you add the option to bet on black and/or green, the solver gives almost the same solution, but puts 0.6% on green and ups red to 11.4%. It appears that green, even with a slightly negative expectation, is such a nice hedge that you're better off including a...

Good call on Excel solver - I'd never used that before. I get 8.1% on 16 5.4% on 14 10.8% on red

That makes sense...

One thing I will note is that Monte Carlo simulation tends to converge slowly near Kelly bet because the volatility is pretty high (hence the desirability of betting half Kelly or less). Incidentally, if you're seeing disagreement did you manage to take the max of that function? If so I'd be...

That's your ending bankroll assuming that case occurred. So you start out with a bankroll of 1 (arbitrary unit). If that case (16) hits, you win 35x whatever fraction of the bankroll you bet on sixteen, lose whatever fraction you bet on fourteen, and win whatever fraction you bet on red. The...

The underlying math of Kelly criterion is that you maximize the expected log of your bankroll. So I actually typed slightly the wrong thing. I should have typed: f(S,F,R) = 4/37*log(35S - F + R + 1) + 3/37*log(-S+35F+R+1)+16/37*log(-S-F+R+1)+14/37*log(-S-F-R+1) Oops - I pulled out the log...

Incidentally, assuming no cheating the ratio of what you should bet is S = fraction of bankroll bet on 16 F = fraction of bankroll bet on 14 R = fraction of bankroll bet on red maximize f(S,F,R) over the range 0 to S+F+R < 1 using gradient=0 method where f(S,F,R) = ln(4/37(35S - F + R) +...