Blog Archives

07 Oct 2022

Glance at Q-Learning

This talk is split into three parts. First an introduction to why as an energy engineer I’m so excited about machine learning. The second part is an introduction to reinforcement learning and Q-Learning specifically. The third part we take a look at a landmark paper in reinforcement learning, DeepMind’s 2013 paper using Q-Learning to play […]

07 Oct 2022

Variety of algorithms used to convert content metadata

The talk will present the detail behind Telegraph AI (Audience Interest), a data driven advertising product. It will focus on the role of algorithms in the process of building it. From building a classification model to annotate content with themes, how we use topic tags in understanding people’s interests and what algorithms we use to […]

07 Oct 2022

Why header bidding is changing everything

Header bidding is the latest in a long line of technologies that disrupt the programmatic ad market. As a major technology platform in the programmatic space, Criteo is seeing first-hand how these changes can affect publishers, advertisers, and everything in between. We’ll see how header bidding has developed, what it means, where it’s going, and […]

07 Oct 2022

Data Mining for Optimizing Content Caching and Distribution

As a leading travel marketplace, Skyscanner is serving a daily load of up to a dozen billion flight itineraries to its users across the globe. The distribution of travel quotes at such a scale requires caching mechanisms optimised for minimising the load on the partners (airlines and travel agencies) and maximising the relevance and comprehensiveness […]

07 Oct 2022

On the Use of Embeddings in Search

One of the main innovations rediscovered in the last years in search and machine learning is the concept of Embeddings. In search, embeddings have been used in many different applications including retrieval, advertising, and recommender systems. In this talk we are going to show some applications of vector space embeddings that have considerably improved the […]

07 Oct 2022

The Data Science Journey in DfT

Tom Ewing is Principal Data Scientist for DfT. He has 20 years’ experience in government in a variety of data, analytical and digital roles and currently relishing the challenge of kickstarting the DfT’s data science capability and making the UK the worldwide leader in digital transport.

07 Oct 2022

The elements of a Data Science career at The Trainline

Panel discussion on how to successfully build a Data Science career, featuring: Gianluca Campenella – Founder Estimand Consulting / Research Fellow Imperial Tom Ewing – Principal Data Scientist – Department for Trade Fergus Weldon – Data Science Team Lead – Trainline David Loughlan – Founder – Data Idols

07 Oct 2022

How to become a Kaggle #1: An introduction to model stacking

Ever wondered how Kaggle masters combine hundreds of different machine learning models to win modelling competitions? Ever wondered how to become ranked #1 on Kaggle? StackNet has helped me do that! StackNet is an open-source, scalable and automated meta-modelling framework that combines various supervised models to improve performance. Written in Java, this library automates many […]

04 Oct 2022

One by one is no fun, lessons learned writing Kafka ETL jobs

I’ve been writing ETL jobs using Kafka for a couple of years now. In that time, I’ve done just about everything wrong, before figuring out what does work. This talk will cover: -What Kafka is -What the major frameworks are, and how they steer you towards one-by-one message processing -Why you shouldn’t do that, including […]