Hot answers tagged

3

In full generality this is a very difficult question. The closest you will get to a general framework is Vapnik-Chervonenkis theory. You can read about this in Chapter 7.9 of "The elements of statistical learning" by Hastie, Tibshirani and Friedman which can be downloaded from their website . But be warned that this is a theoretical approach. Often more ...


3

The following is a good way to judge the quality of fits for a model. http://en.wikipedia.org/wiki/Akaike_information_criterion


2

Two volatility processes yield a higher flexibility of the model. This is of greater importance if one tries to price derivatives with different maturities in one single model. A additional volatility component helps to capture the term structure of volatility, which can depend greatly on time to maturity. See for example the VIX term structure from CBOE: ...


2

I think,the additional volatility factor,$v_2(t)$, provides more flexibility in modeling the volatility surface.We know $\rho$ controls the slope of the implied volatility.In the single-factor Heston model, $\rho$ is constant over maturities,In deed $$Corr[{dS}/{S\,,\,dv]}\;=\rho \,$$ which means that model has trouble providing an adequate fit to market ...


2

Loosely speaking, it can be seen as inserting an additional degree of freedom in the underlying's dynamics. This can be useful from a static perspective: with an additional lever to play on, one can hope to better capture the short term implied volatility smile, which "naive" stochastic volatility models (single volatility factor, no jumps) are known to be ...


2

You are confronted here in the common "bottom-up" or "top-down" problem. I think there is no final answer to your question, as both approach have their pros and cons. For the "bottom-up", you first classify for each feature, then classify again. This give you the ability to get a better understanding of the decision of your algorithm by splitting the ...


2

Use all the attributes in a single model. If you build three separate models, you will be throwing away all all information that might be contained in combinations of different features. So, for example, it might be the case that prices are more likely to go up tomorrow if today's closing price was above the ema and volatility was high, but it is more ...


1

The cross-validation procedure does not turn on the choice of algorithm. Yes - calculate the prediction error of the fitted models when predicting the V'th part of the data. Combine the V estimates of prediction average using a simple average. Subsets should be randomly sampled (roughly equally sized). 2a. Subsets should not overlap. No. As long as the ...



Only top voted, non community-wiki answers of a minimum length are eligible