Blog Posts

LoL: Using "Personality Quizzes" & Nearest Neighbors for Recommendations

Published on: 2nd December, 2021

This is the final in a 3-part series on recommendation methods, however I would consider this actually to be by far the most introductory of any article I’ve written and therefore would recommend starting here. For the experienced of you, I hope there is still value to be had — but you may want to skip a few introductory sections. I’ll make it clear in the article where these points are.

LoL: UMAP and K-Means to Classify Characters — and why it’s useful

Published on: 26th October, 2020

As of today (October 2020) there are 151 “Champions” (playable characters) in the online game, League of Legends, each offering a unique and individual play-style that has made it the single most popular e-sports in the world. Although the variety provides for an engaging competitive environment, it creates complexity for both new players and analysts alike. If every Champion is unique, how is a new player expected to understand the intricacies of every match-up or an analyst meant to summarise the performance of a player?

LoL: Content-Based Champion Recommendations with Dimensionality Reduction

Published on: 19th September, 2020

Today, we’re looking at a different form of recommendation algorithm known as a “Content Based Model”. This technique instead looks to connect items together based on their similarities, i.e. if you’re buying a PS4 sports game produced by EA then here are some other PS4 sports games produced by EA. This technique is favourable when you have no information about user preference, such as when just launching the product.

LoL: Analyzing “Tilt” to Win More Games

Published on: 28th May, 2020

Tilted. A term commonly used among poker players, although it has also been thoroughly adopted by the wider gaming community. Supposedly, it’s origins come from the mechanical pinball machines that would freeze the flippers if the player tried to tilt the machine, sometimes even displaying the warning: “TILT”.

LoL: Graph Networks for Champion Recommendations

Published on: 11th June, 2019

Let us imagine you worked for Riot Games. Your first task is to design a way of generating Champion (playable characters) recommendations in their game, League of Legends. How would you approach the problem?