By @SimonCocking review of Advances in Financial Machine Learning by
Machine learning (ML) is changing virtually every aspect of our lives. Today ML algorithms accomplish tasks that until recently only expert humans could perform. As it relates to finance, this is the most exciting time to adopt a disruptive technology that will transform how everyone invests for generations. Readers will learn how to structure Big data in a way that is amenable to ML algorithms; how to conduct research with ML algorithms on that data; how to use supercomputing methods; how to backtest your discoveries while avoiding false positives. The book addresses real–life problems faced by practitioners on a daily basis, and explains scientifically sound solutions using math, supported by code and examples. Readers become active users who can test the proposed solutions in their particular setting. Written by a recognized expert and portfolio manager, this book will equip investment professionals with the groundbreaking tools needed to succeed in modern finance.
Trading is getting more and more complex. If you had any doubt about this, then Prado’s book clearly illustrates how fast this world is moving, and how deep you need to dive if you are to excel and deliver top of the range solutions and above the curve performing algorithms. Page 225 illustrates in mathematical beauty how complex things already are, if this illustration was in colour it would have near fractal qualities. Other sections clearly illustrate how far into deep mathematical knowledge we already are, and Chapter 21s exploration of brute force and quantum computing is a clear reminder that things are only going to continue to move faster and faster and reacher even higher levels of complexity.
Prado’s book is clearly at the bleeding edge of the machine learning world, but you do also wonder where this will ultimately take us, and it might have been interesting to have had a little more on his thoughts about these trends and how it will play out. He does articulate the opinion that algorithms like these can be of the white box type, rather than proprietary black box technology. However his own role is to perform as successfully for the large ($16 billion worth) amount of funds, so you would imagine it would be hard for him not to aim to ensure the greatest possible returns for the funds under his management. No surprise there, but does this still mean that overall we remain in an ever-escalating machine learning arms race to achieve the best financial investment algorithms possible? These are not questions deeply examined in this book, but you have to wonder if more, faster, sooner is potentially driving us to ever more frequent boom and bust cycles? With this caveat considered this is still an interesting insight into a world that is rapidly becoming more complex than the understanding of any one individual or possibly even company.