Traditional recommendation systems rely on a vast amount of granular customer data to provide effective personalised recommendations to users. In a world where customers are becoming increasingly privacy conscious, how can organisations continue to provide effective recommendations to drive engagement and revenue? Faculty and Springer Nature solved this exact problem, developing a novel reinforcement learning-powered […]
Data Science impact often comes from large-scale automation of many small decisions. In gaming, that can mean who to show which quests, or which power ups to recommend. But models should inform strategic decisions too. What is the impact of different user acquisition strategies over the next 3 years? What’s the minimum retention a new […]
Data Scientists are busy people and keeping abreast of the latest developments in tech and open source is difficult. In this talk, Tom will give an overview of some resources and Python packages which solve key challenges for Data Scientists that have either gone under the radar or haven’t got the traction that they deserve. […]
As mobile app developers seek to monetise their products, in-app advertising has become a popular revenue source. However, there is a risk that ads can hurt user experience and cannibalise in-app purchases, leading to a net loss in revenue. In this talk, we present a novel approach to generating ad revenue without hurting user experience or […]
In this three part online presentation we will describe the world of retail media, with its different channels and their associated particularities. We will then take you through different challenges: from measurement to attribution and optimisation. These will be covered with a media use case in mind, however the science behind them can be used […]
Kubernetes is quickly gaining popularity for managing ML workflows with its load balancing, automatic scaling, and performance optimization features. However, when deploying at an enterprise level, multi-region operations become a crucial consideration for disaster tolerance and performance optimization. This talk will explore the challenges of managing Kubernetes clusters across multiple continents, and showcase real-world examples […]
Join Daniel (ex-YouTube, now a founder at Superlinked) to figure out how to use vector embeddings to build engaging, explainable and safe software – both if you are a generalist engineer looking to get started or seasoned veteran looking for more advanced tips and tricks. For years, data engineers have understood that it is a […]
A/B testing is widely recognized as the most reliable method for establishing causal relationships between interventions and outcomes. However, this method requires a randomly assigned control group, which may not always be possible in practice. Additionally, A/B testing may not be optimal when trying to measure the impact of interventions that have already occurred but […]
In the fast-paced world of data science, the need to develop and retain top talent has never been more critical. The shortage of skilled data professionals in the market, along with the rapidly evolving technological landscape, makes the challenge of building, nurturing and scaling effective data science teams even more significant. In this talk, we […]
