Hot answers tagged prediction
13
First, let's speak about perceptrons in general:
their input $X_0$ is a $K$-dimensional vector. So if you want to use $(P_{bid}(t),P_{ask}(t), Q_{bid}(t),Q_{ask}(t))$, it would mean that without any effort (but later we will see that is would be better to do some efforts, as usual):
$$X_0(t)=(P_{bid}(t),P_{ask}(t), Q_{bid}(t),Q_{ask}(t))'\in\mathbb{R}^4$$
...
3
There are two excellent choices for implementing prediction markets:
(1) Use book orders that stand until filled, just as intrade.com does.
(2) Use an automated market maker (like Robin Hanson's) that stands ready to make trades.
The book orders model is very simple to implement, but can suffer from very wide Bid/Ask spreads. And, it can be tough to bet ...
3
I think this one has a clear answer (I am solely talking about equities here):
The change magnitude is much more predictable than the direction.
The reason being that equity volatility is much more predictable than equity risk premiums. Volatility is nothing else but change magnitude and due to the stylized facts of volatility clustering together with mean ...
2
The two components you refer to in your questions are:
Market direction (the sign of the return)
Change magnitude (the absolute value of the return)
First, I'm sure you realize that neither of these are predictable at a 100%, otherwise there would be no way to make profit (you make profit by seeing things other didn't).
To answer the question, I would ...
2
You should never start out asking how much data you should incorporate in your research effort. You should start with the following points:
Make sure you understand the difference between sampling size to specify your model and data used to run back tests over. Those are entirely different animals.
First, think about your end goal, what are you trying to ...
1
It's a bit unclear to me what you're trying to do, and maybe a better place to ask your question is Stats.SE but I would encourage you to go and have a look at this online class on machine learning which provides an implementation of the backpropagation algorithm.
You can either register or hit preview and go to the NN:Learning chapter, but I would ...
1
I am not sure any of the other answers mentioned this but the main reason you should not use an option model to buy/sell the underlying (BS or other) is that the option models are more about market-making in options and hedging using the underlying rather than forecasting the underlying.
The layman way to understand this is that: using an option model, you ...
1
One possibility worth exploring is to use the support vector machine learning tool on the Metatrader 5 platform. Firstly, if you're not familiar with it, Metatrader 5 is a platform developed for users to implement algorithmic trading in forex and CFD markets (I'm not sure if the platform can be extended to stocks and other markets). It is typically used for ...
Only top voted, non community-wiki answers of a minimum length are eligible
