Christina Maniati currently works as a data scientist consultant within Capgemini's UK Insight and Data service line.She is currently engaged in leveraging a cloud based Hadoop architecture for a global CPG multinational on their People Data Centre Programme for data science program. This multi project program is to allow the company to engage with 1 billion consumers globally through a variety of touch points (Social, Digital, Carelines etc.). This combines both real time Earned Data (Social and Twitter compliance) together with Paid (Digital Advertising), Owned (clickstream) and internal (POS, ERP) datasets. This ground breaking project also covers processes such as Agile delivery, Infrastructure as Code and DevOps (continuous integration and deployment) across full Dev/QA/Prod instances.
Stuarts blog discusses the dependency data scientists have on data preparation and conformity, Master Data Management, including advanced techniques such as entity resolution using probabilistic matching.