I’m benchmarking how long it takes to fit a mixed effects model using lme4 in R, statsmodels in Python, plus showing how MixedModels.jl in Julia is also a viable option. Enjoy these types of posts? Then you should sign up for my newsletter. It’s a short monthly recap of anything…

For those that don’t know Taskmaster is a game show where 5 comedians compete in a variety of nonsensical tasks to win points from the Taskmaster. Most of the time the tasks are creative, (draw a horse while riding a horse) or time-based (burst all the bubbles on some bubble…

In my last blog post I showed how the odds can be used to measure the difficulty of a football match. I then took this difficulty and investigated how predictive it was for the outcome of the match (not very predictive) and the goals/shots taken in the match (more predictive). …

How do we quantify the difficulty of a soccer match and can we construct a single number that will explain how easy or hard the match is for a team to win? I think we can approach this by looking at the match odds and coming up with a way…

Last time I showed you how to set up a producer/consumer model to build a database of BTCUSD trades using the CoinbasePro WebSocket feed. Now I’ll show you how you can connect to the same database to pull out the data, use some specific timeseries database queries and hopefully show…

QuestDB is a timeseries database that is well suited for financial data. It is built with timestamps in mind both when storing the data and also when getting the data out. This makes it the ideal candidate as a storage system for crypto trades. You might have heard of KDB…

This post serves as an introduction to the technique of double machine learning. I replicate an influential paper in R and show how you can use machine learning techniques to help untangle causal effects in data. If you like this type of thing you should sign up to my free…

My dirichletprocess package for R has the ability to fit Infinite Hidden Markov Models using a Dirichlet process. To demonstrate this functionality I will fit a Hidden Markov model to some financial data to see how the states change over time and hopefully highlight why this might be useful. The…