The Blade and Handle of Energy: Cutting Edge R&D and Data for Energy Assets and Markets Watch to hear from two perspectives of utilising data at EDF(UK) to deliver energy to our customers. The blade is R&D where we are exploring cutting edge tech in AI and computer vision to explore how we monitor and […]
At Hymans Robertson we take great pride in providing award-winning independent services to employers, trustees, and financial institutions, offering expertise in pensions, investments, benefits and risk consulting. We’ve made it our mission to help clients secure better financial futures for their businesses, people and customers. And we’re increasingly turning to data as a tool to […]
Lightning talk 1: BuzzWords: How Bumble does Multilingual Topic Modelling at Scale, Stephen O’Farrell, Machine Learning Scientist With the abundance of free-form text data available nowadays, topic modelling has become a fundamental tool for understanding the key issues being discussed online. We found the state-of-the-art topic modelling libraries either too naive or too slow for […]
Please note that this session was NOT recorded. Level: Beginner to Intermediate Delta Lake is the next-gen unified analytics engine designed to build robust production data pipelines at scale. In this hands-on training session, you will learn how Delta solves a multitude of Data Lake challenges, explore how to easily work with complex data, and […]
Creating a good quality labelled data set is a challenge faced by most data scientists, particularly those working in NLP. While raw text data might not be in short supply, most tasks will require this data to be labelled. This often has to be done, rather laboriously, by hand. This talk follows the process of […]
Planning resource to pick, pack and dispatch online orders in fulfilment centres currently relies on a manual forecast with accuracy opportunities. We use data science to provide a more accurate demand forecast for online sales to reduce fulfilment costs and protect the customer delivery time. Interpretability is critical to explain machine learning models and to […]
Today it is becoming more difficult to track the effectiveness of marketing interventions due to rapidly changing legislation that protects privacy, and recent historical events that make the past a poor predictor of the future. This talk outlines the perils of naively trusting machine learning-based solutions to attribution and shows how causal learning can help […]
The concepts and methods of mathematical programming underlie many machine learning algorithms and yet remain relatively unknown outside the operational research community. After a brief overview of optimisation theory, we will introduce the standard-form linear and quadratic programmes. We will then formulate the well-known linear regression problem (and the lesser-known robust regression problem) as mathematical […]