Slow burning, ground breaking and blockbuster data applications at the BBC
Optimising demand and resources for data science, data engineering and analytics products in a large organisation.
Blog Archives
Advanced causal inference made simple
Causal inference, that is estimation of impacts of actions, is a powerful analytical approach that has been getting a lot of press recently. The difference to classic supervised ML is that the impact of an action is never possible to observe directly at single data point level, as we never observe the counterfactual outcome – […]
Climate Panel: Can tech save the world?
SCHEDULE (GMT) 6:00pm – Intro 6:05pm – 4 lightning talks (10 mins each) 6:45pm – Panel discussion and community Q&A 7:15pm – Close Laurence Watson: Improving access to climate data Climate is rightfully getting the attention it deserves, but for innovation and interventions to thrive we need good data. Subak’s community of not-for-profit innovators have detailed many […]
Graphs and Transformers: Exploring the Next AI Frontiers
The spectacular progress of deep learning over the last 15 years has been driven not only by the ability to harness massive computational power, but also by leveraging two relatively old abstractions. While these models are still used, the last five years have seen the emergence of graphs and transformers as fundamental building blocks of […]
Co-op – Community Wellbeing Index – Using data to do good
Please note that this session was NOT recorded. The Community Wellbeing Index (CWI) is an online insight tool that provides wellbeing related information for over 28,000 communities across the UK. There are more than 50 different indicators within the Index, covering a wide range of themes – from the quality of education and transport links […]
Needles & Haystacks: Machine Learning with Imbalanced Datasets
The unique skill of a Machine Learning model is to identify specific instances that humans would easily miss. That needle in a haystack that can make or break your business. But how can you train a machine learning model when the data points you need to identify are extremely rare? Fortunately, this problem is not […]
Classification Guru The Dangers of Dirty Data
Classification Guru The Dangers of Dirty Data by Susan Walsh We all think we know what bad data looks like, but what is it and what are the consequences? With a decade of experience fixing your dirty data, Susan Walsh is the Classification Guru. Susan is Founder and Managing Director of The Classification Guru Ltd, […]
From team building to emotion detection in 4 weeks: lifting the data bottleneck for deep learning
From team building to emotion detection in 4 weeks: lifting the data bottleneck for deep learning by Louis Dominique Vainqueur, Digitas Using pretrained models to solve natural language processing use cases has become commonplace in businesses. But pretrained models have limitations. In this talk, the Digitas team will share the lessons learned from building a […]
Using data science to forecast sales for a £10B retailer
Using data science to forecast sales for a £10B retailer by Behzad Bordbar, M&S Forecasting is a vital cornerstone activity in retail. Day to day tasks such as Supply Chain Management, Labour Planning and Price Markdown are not possible without precise forecasting. For large retailers such as M&S, forecasting at scale is a non-trivial task. […]