I came across a post about forecasting volatility with a neural network; Honchar "Neural networks for algorithmic trading. Volatility forecasting and custom loss functions". However, it is not clear to me how the architecture is chosen.
$\begingroup$
$\endgroup$
1
-
$\begingroup$ I am not an expert, but I doubt one should ever waste his time with articles full of poorly commented (if at all) code with a lot of "let's try this one" sentences, unless you're courageous enough to skim through non-scientific writings. $\endgroup$– BS.Commented Sep 1, 2018 at 12:12
Add a comment
|
2 Answers
$\begingroup$
$\endgroup$
- I don't know, and the author doesn't say.
- I don't know, and the author doesn't even say what $f$ is.
- I don't know, and given points 1 and 2 above, I don't see the point in digging through the paper to see whether the author ever says.
I doubt this paper will be very helpful. But it lists the author's email address, so you could contact him directly.
answered Jul 17, 2018 at 5:29
$\begingroup$
$\endgroup$
2
There's an entire "How to predict the stock market with neural networks" cottage industry now that seems to have little to do with sound financial principles or rigorous time series analysis and everything to do with the current Deep Learning/Tensorflow hype. The blog post you mention seems to fall squarely within that category.
That being said, some serious work on forecasting volatility with NNets has been done. See for example:
- Xu, Q., Liu, X., Jiang, C., & Yu, K. (2016). "Quantile autoregression neural network model with applications to evaluating value at risk" - Applied Soft Computing
- Borovykh, A., Bohte, S., & Oosterlee, C. W. (2017). "Conditional time series forecasting with convolutional neural networks" - arXiv preprint arXiv:1703.04691
answered Sep 25, 2018 at 15:07
-
1$\begingroup$ Purely as a pedagogical tool, it makes sense to use the stock market as an example problem because (1) data is readily available; (2) everyone understands that the core trading task is to accumulate returns; (3) it's widely believed that all relevant information about a asset is recorded in its price. As a toy problem, is really easy to present stock trading as a practical use-case for NNs, even if the models themselves won't generate a profit. But I agree that hype can cause people to overlook the reasons toy NNs are poor tools for producing healthy returns. $\endgroup$– Sycorax ♦Commented Sep 25, 2018 at 15:26
-
1$\begingroup$ But that said, I still upvoted. (+1) $\endgroup$– Sycorax ♦Commented Sep 25, 2018 at 15:45