I have access to some tick data and Bloomberg data. Outside of data mining and hoping to find an economic rationale after the fact, what do you usually do to generate ideas before you look at the data? I'm having trouble thinking of anything outside of arbitrage, trading pairs of similar assets, data mining correlated assets, data mining stuff that mean reverts, and data mining "signals" from tick data. Maybe I'm just overthinking and data mining actually works. What are some general strategies that firms actually employ as opposed to strategies fit for the personal trader?

I've heard about stuff on momentum (last 11 months skip a month) and the typical "factor" models like small - big, liqudity, but that seems more suited for like mutual funds.

I guess another question is, do firms actually data mine a lot? I'm trying to get a job so I want to do something that is relevant/practical that I can talk about in an interview as opposed to just "I took a stats class or watched a video on ML".

Should I be digging into random research papers? I mean I have ideas in general, but I only have access to some tick data and Bloomberg - which is pretty limited since it only offers closing values which can be a different timestamp for different products/exchanges.


  • 1
    $\begingroup$ It's an extremely difficult question to answer because, if anyone does have any good ideas, they're not going to divulge them anyway. My advice would be to get a job where you work in the field ( if you haven't in the past ) and, depending on the job, you might get some good experience and some good ideas. But, even then, a lot of places will make you sign an NDA and make it very difficult to leave etc. Read the paperback "head of research" if you want to get a better idea of what the field can be like. $\endgroup$
    – mark leeds
    Jun 3, 2020 at 3:34
  • $\begingroup$ Thanks. Obviously no on will disclose any good ideas but was curious if there are any systematic approaches to idea generation. $\endgroup$
    – confused
    Jun 24, 2020 at 2:17
  • 1
    $\begingroup$ @confused: The closest thing I've seen to disclosure in quant is ernest chan's books. I forget the names but, if you google on amazon, they'll come up. I only read the first one but I remember being pretty surprised at the level of open-ness. $\endgroup$
    – mark leeds
    Jun 24, 2020 at 4:35
  • 2
    $\begingroup$ sounds good. the last part you talk about is called "market-microstructure". a lot of work in that is currently done by econo-physicists. I don't know much about it but bouchard and doyne farmer and lehalle are some of the big names in that. In fact, lehalle is on quant.stackexchange and seems like a very generous person as far as providing relevant references and useful info. $\endgroup$
    – mark leeds
    Jun 30, 2020 at 5:19
  • 1
    $\begingroup$ The three people I mentioned are prolific. tons of publications and, not their fault, but it can be somewhat difficult to get one's head around all of it. you may want to get bouchard's latest text. I forget title but you'll find it on amazon. ticks, quotes, trades or something like that. $\endgroup$
    – mark leeds
    Jul 1, 2020 at 16:34

1 Answer 1


It is a very broad question, let me narrow it and answer on overfitting: how can you prevent blind applications of black box models to exhibit only in sample anecdotes?

First of all, it is worthwhile to focus on two terms

  • black box model is not mandatorily a deep neural network, it can be a sequence of moving averages, ranks, and truncations (that is indeed very non linear); a model is a black box when it cannot be explained? here we meet the ambition of Explainable AI. This is not that new: when you use mutual information the measure the relation between two variables (one you observe, one you want to predict), you can end up with the answer that "yes, there is a relation", without being able to exhibit an operative model....
  • anecdotes are simply descriptive and not explanatory. It is like witnessing that "you observed a new star in the sky", without giving an understanding of the trajectories of all stars of this kind (to take an image that will speak to econophysicists). This has been theorised by Thomas Kuhn in The Structure Of Scientific Revolutions, be has been also formulated by Shannon and Kolmogorov a more formal way: knowledge has to do with "compression of information" whereas anecdotes are repetition of information.

How van you prevent these issues?

  1. Have a lot of data: you can preserve out of sample datasets to test and then validate your models. That is why, in finance, tick data is a nice playground: you have so many observations.
  2. Regularize your model either by standard penalisation statistical learning uses for long (see Lasso or Ridge), either by a story that explains what you think you leverage on (the story should be reflected in the variables you select, the way you preprocess and mix them). The more constraints you put around your modelling, the more robust will be anything you find despite the constraints.

Let me finish by an example (on tick data), the two papers:

The first one is a very well done black-box model to predict some features of order book dynamics. And the second (Justin being (co)-author of both, that is why the example is interesting), explain why it works. You can consider the first as a technical trial, and the second as a finite product. Of course what is the best is when the explanation has been formulated before the explorations, or when the explanation are so string that they can be (roughly) tested with simpler models.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.