Data Visualization, Machine Learning

In the fifth article of this series, we will continue to summarise a collection of commonly used technical analysis trading models that will steadily increase in mathematical and computational complexity. Typically, these models are likely to be most effective around fluctuating or periodic instruments, such as forex pairs or commodities, which is what I have backtested them on. The aim behind each of these models is that they should be objective and systematic i.e. we should be able to translate them into a trading bot that will check some conditions at the start of each time period and make a…

22 weeks later, the NFL season is finally finished and we can sit back and take stock of everything we’ve just witnessed. As has long become the norm in the league, Tom Brady won his 7th ring, this time with the Buccaneers. A truly dominant performance on both sides of the field, the Bucs won this game from start to finish. This article will present a statistical recap of the game, going over the talking points and presenting the analytics to support this.

Key Terminology

• YAC — Yards After Catch
• xYAC — Expected Yards After Catch
• EPA — Expected Points Added per…

Opinion

The NFC Championship last week saw the Buccaneers move forward to the Super Bowl, marking the 10th time Tom Brady has competed for a ring. The game was close and in the second half the Packers had more than a few chances to close the gap, but ultimately couldn’t do enough to prevent going home. This article will discuss some of the statistical trends from analysis of the play-by-play data from the game.

Key Terms

• YAC — Yards After Catch
• EPA — Expected Points Added per Play
• WPA — Win % Added per Play
• EP — Expected Points (can be calculated as…

Opinion

Certain candlestick patterns have been found to be potential indicators for trend reversals across a wide array of markets. We sometimes run into an issue, however, in that, with the huge number of options we have available to us in terms of currencies equities, commodities, etc. we may miss out on catching these reversals, essentially leaving money on the table when we could have jumped on a trend right at its apex. This article represents the first step of systematizing these patterns so that we can roll them out for hundreds of markets without having to actually keep our eyes…

Data Visualization

If you enjoyed this content, I’m launching a new algorithmic finance newsletter, called Algo Fin, that you might be interested in. This newsletter will explore the connection between data science and finance, with an initial focus on the currency markets, but I hope to build many more avenues in the future. The newsletter is free to join currently as I am still planning a launch for paid subscribers, so if this sounds like something you might be interested in, its definitely worth checking out here!.

In the fourth article of this series, we will continue to summarise a collection of…

This is the first article in a series in which I will present a pre-modelling look through different datasets. The goal of these articles is to stress the importance of understanding data before you serve it to an ML model.

Introduction

The goal stems from the understanding of how common ML models are built. Regressions, Neural Networks, Support Vector Machines and Decision Trees are models that utilise the fundamentals of linear algebra in an iterative and self-improving way. The maths behind a single section of these models is relatively simple, a neural network for example can be thought of as a…

This article is a continuation of a series I am writing on key theoretical concepts to Machine Learning. The other articles in this series are available on my page.

Machine Learning is the development of algorithms that learn from information. They study relationships within the data presented to them and use this to then predict the nature of unseen outcomes. In the same way that we do as humans, computers learn with experience. It follows this that computers require high quality information for them to make correct assumptions. Because traditional machine learning models don’t have the ability to adjust their…

This article is a continuation of a series I am writing on key theoretical concepts to Machine Learning. The other articles in this series are available on my page.

Unsupervised learning, also known as pattern recognition, is a method that attempts to find intrinsic patterns in a dataset without an explicit direction or end point in the form of labels. In colloquial English, in a supervised learning problem, we might tell a model to “find the optimal general path from a set of inputs to the exact desired outputs (in classification) or as close as possible to the outputs (in…