AI & Machine Learning

The majority of Data Science projects fail. The reasons for the high failure rate are many and varied. However, as surprising as this may sound, one of the main reasons is the lack of clearly defined project goal(s) and the associated requirements.

This blog post gives you a better intuitive feel for what graph embeddings are and how they are used to accelerate real-time analytics. Within the next few years we will see graph embedding take center stage in the area of innovative analytics.

There are dozens of companies that lost their customers due to a million tiny issues or a couple of big ones. This article shows how Machine Learning can help predict customer churn.

By now, you have already gained enough knowledge and skills about Data Science and have built your first (or even your second and third) project. At this point, it is time to improve your workflow to facilitate further development process.

This post argues that the graph isomorphism setting is too limiting for analysing the expressive power of graph neural networks and suggest a broader setting based on metric embeddings.

Linear regression is about finding the line of best fit for a dataset. This line can then be used to make predictions. Gradient descent is a tool to arrive at the line of best fit.

This post discusses how to design local and computationally efficient provably powerful graph neural networks that are not based on the Weisfeiler-Lehman tests hierarchy.

This is a comprehensive tutorial on handling imbalanced datasets. Whilst these approaches remain valid for multiclass classification, the main focus of this article will be on binary classification for simplicity.

Do you have a feeling that deep learning on graphs is a bunch of heuristics that work sometimes and nobody has a clue why? In this post, I discuss the graph isomorphism problem, the Weisfeiler-Lehman heuristic for graph isomorphism testing, and how it can be used to analyse the expressive power of graph neural networks.

This article compiled a large collection of inspirational quotes on data science. The quotes are categorised alphabetically. Hopefully, these words of wisdom will bring perspectives and inspire your data science journey.

Predictive analytics used to be in the domain of more technical employees, but today, no-code automated machine learning (AutoML) tools mean anyone can deploy AI.