Tag Info

Hot answers tagged

19

Because of: The (extreme) dominance of noise over signal The prevalence of non-repeating patterns (many of which we know are not going to repeat) A pathetic sample size for cross-validation Regime changes due to exogenous events. These are typically in the cross-val window which makes it even worse. (GFC, financial integration, trade law changes, interest ...


3

I was going to comment but it turned out to be quite elaborate. My experience with certain AI/ML methods is that they're not deterministic. Take RBM for instance, a very wide-spread paradigm. To train such a machine you have two approaches, backpropagation or Kullback-Leibler divergence. Both require you to initialise the machine to a random state. And ...


3

As with many machine learning technologies, you can run a separate training and testing phase before deploying it live for prediction. All it does is build a collection of decision trees based on the parameters you give it - if the output field is a factor, you get classification (a finite enumerated set of values); if it's numeric, you get prediction. One ...


2

There is no right approach a priori. Try all approaches that make decent sense and pick the one that maximises a utility function on out of sample PnL and risk (or some similar decision rule).


2

Scale and range are your biggest issues. If one input has values which range from e.g. 2300-3500, and another from 0 to 18, then the large scale of the first will swamp the other and provide greater informativity into your learning algorithm. Therefore, normalize into range [0,1] or mean-zero standardize - like you have already done. Be careful with ...


2

You're thinking about this the wrong way, in my opinion. Win/loss percentage is worthless in isolation. You must consider the symmetry of your winners and losers. You can have a win % of only 40% and still have a wonderful strategy if your your winners are significantly larger than your losers (this is the classic trend follower PnL distribution). So, you ...


2

It's probably because of the strong long-standing statistical underpinnings in economics and econometrics, and overall, risk prediction. For example, look at current research with fat-tail distributions and calculations for Expected Tail Loss (ETL), etc. These studies fit Student's t, Normal, Stable, and Pareto probability distributions to data and report ...


1

Such an approach is done by the systemic investor blogger in his blog Time Series Matching with Dynamic Time Warping.


1

I'm not sure that machine learning would lead to any practical solutions here. Do you really have enough data for that kind of techniques? I would suggest a different approach: assume that the exercise is optimal, but just based on a different cost function than the expected pay-off. If you can find a function that replicates well enough the past exercise ...


1

Your question is too broad, but I there is plenty of examples of uses of machine learning to mimic human behaviour. For instance deep learning has been used 25 years ago to read checks in banks, or support vector machines 15 years ago to implement artificial vision, or bayesian networks to mimic expert diagnosis. I guess it would not be that hard to use ...


1

There can be several reasons for this: The "new data" that you use post-training & post-validation is not drawn from the same distribution as the one that you used to create/draw your training, testing and validation data. Since you have not mentioned anything related to the input features in your data-set, I am assuming that the ...


1

You will find that the level of success you have using Neural Networks (NN) as a tool for financial market prediction is strongly dependent on what initially appear to be some quite subtle factors. In particular: Input data: You mention using "certain technical indicators". I assume that you mean the standard TA set of price-based indicators such as Moving ...


1

Neural networks are a supervised machine learning algorithm. Unlike unsupervised machine learning, the key to supervised machine learning is the selection of input factors and explicit labeling of outputs. Input factors have to be manually selected, such as your combination of technical / fundamental / statistical indicators. Outputs have to be ...


1

A classifier can be weak for a number of reasons, and it mainly depends on characteristics of the data. For example, if the data are not linearly separable, then linear regression will be weak (poor correlation between predicted class and true class labels). However, if the data are linearly separable, then other classifiers may not work as well as linear ...


1

If I correctly understood, you have a big training set and EMD calculated over the whole set at once. Then you use a part of training set and the corresponding part of EMD to infer prediction. The problem here is that you peep into the future having EMD on the edge of the working window calculated using information out of the window. Hence, surely you should ...


1

It could help with things like fraud detection, analysis of bankruptcy probability, default risk, unsupervised learning for qualitative/descriptive purposes, or for a purely backwards looking supervised analysis on returns again for descriptive/understanding purposes (variable important, etc, perhaps impulse response analysis). It may also be good at ...


1

This is an pretty general question You are essentially asking how to estimate the regression function $$Y[t]-Y[t-1] = m(X_i [t], ..., X_p[t]) + \epsilon[t]$$ without any additional structure. Here is a basic list of questions to consider. Keep in mind that the more you can guide these procedures with domain knowledge the better your results will likely ...



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