# Modeling stock market signals (online changepoint detection)

Hi everyone. I am working on a finance problem. I have a time-series for each stock that tells me how much of it I should buy or sell on any given day. The problem is that the signal is noisy and if I react to the noise, I am getting punished by the brokerage commissions without any perceptible reward. It seems like I need something to tell me whether the signal has really changed (and if so, then by how much). Then I can make an intelligent decision on whether I should adjust my portfolio, and if the expected reward exceeds the transaction costs.

In the Bayesian context, I see multiple references to this 2007 paper by Adams and MacKay, in which they model the â€śrun lengthâ€ť of a time-series regime. The paper is elegantly summarized in this blog post, as well as this talk, which also proposes a computationally efficient way to calculate the most likely path through the time-series regimes. I believe the speaker is referencing this GitHub, authored by the aforementioned blogger that contains a numpy/scipy implementation of the Adams / MacKay algorithm.

Anyway, I donâ€™t have a strong quantitative background, so it is hard for me to understand the basic theoretical underpinnings, let alone to implement the code in PyMC3. However, I thought that online changepoint detection must be a frequent enough use case that perhaps others, who are more versed in Bayesian statistics, would be interested in taking a look and weighing in on what the PyMC3 framework would look like. I also thought that for my specific problem I can start with a simpler solution, like GP smoothing. At this point, I feel that any advice from you guys would be super helpful. Thanks!

Here are a couple other GitHubs with numpy/scipy implementations: one (notebook, seems informative), two (claims performance improvement over what is in the first link)

Also, hereâ€™s documentation for the graphlab implementation: link

Model like this is probably pretty difficult to implement in pymc3 as it involves dynamic expanding the parameter set. You can translate some of the component into pymc3 tho.

1 Like

Understood. Thank you.

Iâ€™ll see what I can piece together in numpy/scipy. And if I can get an improvement with simpler solutions (smoothing) in pymc3.