- This event has passed.
SDST Meetup: ‘Data Transformation’, and ‘Heterogeneous Methods For Heterogeneous Data?’
24th October 2019 @ 6:30 pm - 8:45 pm
Angus Neilson – Technical Architect at Wood Mackenzie
Working for the last year + on the new data platform for Wood Mackenzie with a focus on data ingestion framework and processing using Kafka, Python, Java and AWS Serverless. Keen interest in Data Engineering.
The Metamorphosis of Data at Wood Mackenzie
Wood Mackenzie have been on a journey of transformation from a highly influential but traditional Data Analyst business to becoming a leading technology company providing insights at scale to customers and partners in the global energy sector. From ingestion and processing to delivery to their Wood Mackenzie Lens® platform (https://www.woodmac.com/research/lens/). Angus will be focusing on the data platform which is being built at Wood Mackenzie and the journey that they have been through using a range of different technology. He will be talking about how the technology that they are using and how it is essentially going to benefit their data teams, the way data is uploaded, stored, shared, analysed and distributed to their clients.
Dr Anastasia Ushakova, Computational Social Scientist and Teaching Fellow in Statistics, University of Edinburgh
Anastasia is a Teaching Fellow in Statistics at the University of Edinburgh. Her PhD research, in collaboration with one of the large domestic energy providers in the UK, was concerned with big data analysis of smart meter data.
Find more here: aushakova.com
Heterogeneous methods for heterogeneous data?
The fact that we are living in the age of data is not new to anyone. However, rarely do we come across a complete and inclusive understanding of what contributes to data heterogeneity and how this impacts data collection and the analysis. The tendency is to assume that forms of big data are more or less alike: volumous, relational, variable, and exhaustive. While the data itself may often be not hard to access, how do we collect ‘good’ data? How do we know which modelling techniques would be more appropriate? This talk will present an example of big data for residential energy usage that arrives from smart meters. This complex time series data is novel and highly valuable given both current energy sustainability and management goals. It will be shown that depending on the sample chosen and the choice of methods, one can tell very different stories about the data. The question that talk will try to answer is how one select from this choice, and do we need a specific set of tools tailored to the unique properties of various datasets?
6:30 PM – 7:00 PM: Networking
7:00 PM – 7.30 PM: Angus Neilson, Technical Architect, Wood Mackenzie + Q&A
7.30 PM – 8.00 PM: Dr Anastasia Ushakova, Computational Social Scientist and Teaching Fellow in Statistics, University of Edinburgh
8.00 PM – 8.45 PM: Networking and Drink