Machine learning the mundane

Machine learning the mundane

Try to think of the "buzziest", buzzwords you can think of. Support vector machines? No. Random Forests? No. However, group these together (and much more) under the umbrella of "machine learning", and suddenly we have created a buzzword! The basic idea of many of the techniques which underpin machine learning is find relationships between variables. In particular, we do not need to specify the form of the relationship beforehand (eg. linear). In fact the relationships might be highly non-linear. We need to be careful though that we are not data mining too much, and end up fitting to noise. For example, let's say that there's generally linear relationship between two variables. If we have a very small number of observations, the "best" fit found using a machine learning technique could involve actually joining up the points, as opposed to doing a straight line of best fit. This will obviously fit nicely in our sample, but then when we throw new data in, we will likely find that a straight line of best fit could work better. The difficulty with finance is that relationships tend to be less stable (financial time series are not stationary), and often we don't have sufficient data. There is a trade off between optimal solutions in sample, and robustness out-of-sample when we create a trading rule. In other words, we want to have at least some fitting, but equally, overdone and it will just look on paper and not when we're actually running real money.

A funky way to use machine learning might be to infer trading rules directly and this is often the most obvious question to ask. Throw in many, many features based on market data and similar datasets, and see if it can infer trading rule which maximise P&L. However, this is very difficult to get to work, in a live out-of-sample setting for the reasons described above. In practice, we have a better chance of success (out-of-sample) if we create features which we think have an intuitive rationale. Some of these might be based on alternative datasets. We might also use machine learning to classify different types of market, to help us to overweight or underweight signals.

Perhaps a less glamorous way to use machine learning in finance, is to help with the mundane tasks. ...

To read the rest of the article on the Cuemacro website click here

要查看或添加评论,请登录

Saeed Amen的更多文章

  • Learning from running financial models live

    Learning from running financial models live

    Let's say you are the world's best burger chef (we all have ambitions, right). You'd be serving up all manner of…

    1 条评论
  • DeepSeek, objectives and constraints

    DeepSeek, objectives and constraints

    When a new burger joint opens up, there's often a buzz. Everyone (well, at least me) wants to try the new burger.

    1 条评论
  • Hundreds of quant papers from #QuantLinkADay in 2024

    Hundreds of quant papers from #QuantLinkADay in 2024

    I tweet a lot (from @saeedamenfx and at BlueSky at @saeedamenfx.bsky.

  • What we’ve learnt from reading thousands of Fed communications

    What we’ve learnt from reading thousands of Fed communications

    We recently had the last FOMC decision of 2024. Market l participants reacted to the hawkish tone including Powell’s…

    1 条评论
  • Takeaways from QuantMinds 2024 in London

    Takeaways from QuantMinds 2024 in London

    Over the past years, the quant industry has changed substantially. My first visit to Global Derivatives was just over a…

    12 条评论
  • Takeaways from Web Summit 2024

    Takeaways from Web Summit 2024

    Think of Lisbon and no doubt it’ll conjure images of explorers setting sail in centuries past across the ocean, the…

    1 条评论
  • FILS Europe 2024 Takeaways

    FILS Europe 2024 Takeaways

    Paris is home to many things, the Eiffel Tower, the Arc de Triomphe, burgers (ok, I made that one up!). In recent…

    4 条评论
  • Don't look back in hangar steak

    Don't look back in hangar steak

    I'm currently in the queue for Oasis tickets. Rather than mindlessly watching the counter of people in the queue ahead…

    5 条评论
  • The Olympic spirit for forecasting

    The Olympic spirit for forecasting

    The Olympics finally finished, and the Paralympics are about to begin. I managed to go to some of the Olympic football…

  • Eleven years of independence

    Eleven years of independence

    Regrets become ever more edged with the passing of time. Recalling a time long gone, when perhaps a decision made, was…

    5 条评论

社区洞察

其他会员也浏览了