An Overview of My Blog

organization
Author

Cem Sirin

Published

March 26, 2023

This will be an overview of my blog.

This blog is a place for me to share my thoughts and ideas on the world of data science and quantitative finance. I will update this post as I add more content to the blog. I aim to compartmentalize my posts, depending on the topic.

Quantitative Finance (QF)

When it comes to quantitative finance, there is no clear set of topics that it covers. Traditionally, it leans more towards topics like Risk Management, Portfolio Management, and Asset Pricing. Although these topics are still relevant, they sprout from a more traditional view of finance as the main goal is to decrease risk and uphold a high expected return. This goal is formed by the idea that all financial assets obey to Risk-Return tradeoff, that is, the higher the expected return, the higher the risk.

Although, empirically this is seems true in the long-term, it does not necessarily mean that we can not achieve higher returns in the short-term. With the rise of machine learning and more interdisciplinary approaches, many new topics have emerged. The new goal is to increase returns in the short-term, while still maintaining a low risk profile. This is where topics like algorithmic trading and high-frequency trading come into play, and which I will cover in this blog.

Since these fields are quite new, there are no clear compartmentalized topics. One of the most influential books in this field is Advances in Financial Machine Learning by Marcos Lopez de Prado. I think the chapters in this book is a good way of compartmentalizing the topics in this field, so I will follow the same structure. And, while on the topic of books, I also quite like Machine Learning for Factor Investing by Coqueret and Guida, which is also available free online. It is a “bookdown”, which is a book written in R Markdown and I like its User Interface a lot. Anyways, here is the list of topics I will cover in this blog (I will update this list as I add more content :D ):

  • Labelling
  • Model Selection