Reputation
1,189
Next privilege 1,250 Rep.
Create tag synonyms
Badges
1 9 26
Newest
 Yearling
Impact
~51k people reached

Feb
2
comment How are risk management practices applied to ML/AI-based automated trading systems
@Lirik: actually what you really do is paper trade a whole cadre of such agents, then on some date you pick the best one and 'switch it on' with real money. At which point you have datamining bias. Unless, as I have said previously, your system is completely without knobs, has the right data, does not require 'featurization' of said data, and works the first time, you spawn a whole stable of these things, or sequentially fiddle with them until they 'look good'. It doesn't matter what your testing looks like, whenever you use the same data to select and evaluate, you have this bias. period.
Feb
2
comment How are risk management practices applied to ML/AI-based automated trading systems
@Lirik, I doubt anyone is going to trade a magical black box without some estimate of its performance going forward. You do this via backtesting. As I said earlier, either 1) all your code works great the first time you try it, and the backtest looks acceptable (gold star for you) or 2) you keep sequentially refining it and eventually trade on the one that 'performed the best'. You now have datamining bias. Yes, one can train the models in-sample, then trade them out of sample, with rolling retrain, etc, but my statement stands when looking at the system as a whole: get it right 1st time or...
Feb
2
comment How are risk management practices applied to ML/AI-based automated trading systems
@Lirik I doubt that could be the case. Backtest arb can only be mitigated by higher fidelity simulation and good coding. Grue and Bleen can perhaps be tackled by choice of algorithm. The datamining bias, however, remains. Whenever you use the same data to select your strategy and evaluate its performance, you are subject to this bias. If your online ML algo is entirely without knobs and it works the first time you run it, more power to you; otherwise, there will be a sequential process of fiddling with it until it 'looks good' at which point you have your bias.
Feb
1
comment How are risk management practices applied to ML/AI-based automated trading systems
@Lirik these are very serious risks. Beyond that, I am not sure one will have much success e.g. trying to reverse-engineer a black box ML/AI system in order to detect when it has gone haywire. If you are just receiving the trades out of the thing, I am afraid there is not much one can do beyond checking concentration limits and leverage constraints.
Feb
1
answered How can I go about applying machine learning algorithms to stock markets?
Feb
1
asked How do you evaluate a covariance forecast?
Feb
1
comment How can I go about applying machine learning algorithms to stock markets?
survival analysis seems better suited for this kind of thing...
Feb
1
comment Approximately what proportion of a stock’s volatility is explained by market movement?
not a problem. I think I was looking less for 'the answer' (which I can figure out from the data), but for what experts believe, with a given amount of uncertainty on that belief.
Feb
1
answered What is a “coherent” risk measure?
Feb
1
comment Approximately what proportion of a stock’s volatility is explained by market movement?
my question is about the decomposition of variance of the stock returns. If you think about CAPM as a linear regression, I am looking for the $R^2$.
Feb
1
comment Why does the VIX index have *any* correlation to the market?
should there be an observable volume effect because of this? for example, should this imply a spike in trading volume or interest when volatility spikes up?
Feb
1
answered How are risk management practices applied to ML/AI-based automated trading systems
Feb
1
comment How are risk management practices applied to ML/AI-based automated trading systems
This form of the Kelly criterion seems only appropriate for binary outcomes.
Feb
1
comment How to calculate future distribution of price using volatility?
The volatility scales as the square root of time. So in one month, you would have $\sigma / \sqrt{12}$, not $\sigma / 12$. This has nothing to do with being log normal, though.
Feb
1
awarded  Teacher
Feb
1
answered How to calculate future distribution of price using volatility?
Feb
1
asked Is there a standard model for market impact?
Jan
31
asked Why does the VIX index have *any* correlation to the market?
Jan
31
awarded  Student
Jan
31
asked Approximately what proportion of a stock’s volatility is explained by market movement?