Skip to content
All library documents

Planning Machine Learning Projects for Momentum Trading

Article Quant Q&A · Author: user34619
Read the original

Summary

This document is aimed at a project supervisor seeking a broad map of machine learning methods relevant to an algorithmic momentum strategy. It names families such as neural networks, reinforcement learning, regression, clustering, Markov models, evolutionary methods, and spectral techniques, while stressing that these approaches solve different kinds of problems. The central planning advice is to define specific data structures and hypotheses for algorithms to address rather than expecting a general-purpose model to discover profitable patterns from a large dataset.

It highlights backtesting controls: prevent access to information that would not have been available at the time, and evaluate performance on data kept unseen during development. It also describes combining separate algorithms and using optimization methods to choose combinations under a reward or risk objective. The answer is an orientation, not a technical implementation guide or evidence that any named method will work. Strategy performance still requires careful validation against data snooping and realistic information timing.

Key ideas

  • Machine learning covers many algorithm families, and each addresses different problem types.
  • Project teams should define specific hypotheses and data structures for models to investigate.
  • Backtests need to prevent future information from entering historical decisions.
  • Unseen data provides a more meaningful check of performance than data used in development.
  • Separate algorithms can be combined and optimized against a reward or risk objective.

Tags

Machine learningMomentumBacktestingPortfolio construction
Full text
# approach on trading algorithm using machine learning


# approach on trading algorithm using machine learning












let's say I am supervising a algorithmic trading project using machine learning. I don't have involvement in the technical side but am involved in the high level planning.

the style is likely momentum trading.

what are the resources that I can familiarize myself with the topics and what are the major algorithms already available to steer the project/conversations? thanks

## Answer by Attack68 (score 6, accepted)

https://quant.stackexchange.com/a/40273

'Machine learning' describes a very broad spectrum of algorithms. Just briefly here are a few conceptual areas;

- Neural networks

- Reinforcement learning

- Genetic algorithms and genetic programming

- Particle swarm optimisation (PSO)

- Regression models

- Optimisation routines

- Markov models

- Wavelet transforms and Fourier Transform and Spectral Analysis.

- Clustering

You obviously can't go away and become an expert in those overnight but you can get a general feel for the types of problems they solve with a bit of wikipedia.

I suspect you are aware of this already but you can't just collect a massive amount of data, bung it in an holistic 'algorithm' and get results. The best results are often due to well placed conjectures on specific structures in data which precise algorithms seek. Many of the best results we see in 'ai' today are essentially hand-crafted algorithms designed for a specific task on specific data.

You will no doubt encounter two things in your project.

1) Backtesting - Make sure there is a testbed of data that an algorithm has access to and that it has no 'snooping' ability, i.e. it cannot access data that is otherwise not available at the time. A good example is dividend adjusted stock prices when the dividend is an 'unknown future value'. Testing on completely unseen data is the only way to really evaluate the performance otherwise you have biased tests and the results of tests will not match reality.

2) Combination of algorithms. Decoupled algorithms can be constructed and combined, where another algorithm has the responsibility of detecting the best combination. Again usually done via optimising some function like reward/risk of a combination of algos. This is where genetic algorithms / PSO can be employed. Heres a final link to an example of merging different algorithms which had a hybrid reward structure with a fun outcome https://sploid.gizmodo.com/microsofts-ai-just-shattered-the-ms-pac-man-high-score-1796091352 - better link https://blogs.microsoft.com/ai/divide-conquer-microsoft-researchers-used-ai-master-ms-pac-man/#sm.000jjtxcn14wufqgy2q23tdff39d0

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.