Here at Findmypast, we have access to billions of digitised records describing the lives of people throughout history. Each record is a piece of a puzzle that connects individuals together into a vast jigsaw of stories, whether through marriage, bloodline, migration, crime or war. Unfortunately, there’s no picture on the front of the box to guide us – we only have the pieces. That’s the challenge we are setting ourselves at Findmypast – build smart data-driven products that surface this information to our customers in an engaging and intuitive way.
As part of the wider Data Analytics team, Data Scientists at Findmypast are highly valued by stakeholders to interrogate large amounts of data and help the business make decisions in a fast paced environment. We are data evangelists, we work to optimise the product, the conversion funnel and our marketing channels while ensuring key stakeholders are provided with the right (and accurate) information at the right time.
- Manage the workload and output of a highly talented, Junior Data Scientist
- Train & Develop the skills of the Junior Data Scientist
- Support the rest of the Analytics team with their workload and development
- Build high performance predictive models in Python / R
- Embed the output of these models in the business, with a direct focus on improving retention and acquisition.
- Collect data from a wide variety of sources using SQL
- Use regular expressions to parse features out of text strings
- Construct new features that improve model accuracy
Data visualization / interpretation
- Surface output through dashboards built in Power BI / Tableau
- Recommend product improvements as a result of analysis conducted on our customer behaviour database
- Presentation of ideas to C-level executives
Development of new data-driven products
- Design, develop and deploy algorithms that operate on our record sets
- Use of graph databases (e.g. neo4j) to identify stories in family histories
- Liaise with Product and Engineering teams to help develop new data-driven products
The successful applicant will have:
- Experience using R and/or Python to analyse, transform and visualize big data
- Knowledge of data/analytical tools, including advanced Excel skills, SQL, relational databases; aptitude and willingness to learn new tools quickly
- Experience linking data through graph databases such as Neo4j
- Knowledge of machine learning techniques (e.g. recommendation algorithms, classification / regression, clustering)
- Good understanding of statistics and probability
Desirable skills and experience:
- A passion for data science and perhaps a top 10% finish in a Kaggle or similar competition
- Experience with Google Analytics / BigQuery
- Experience with Power BI / Tableau or similar
- Knowledge of graph theory / graph database technology
In return, we offer a friendly, relaxed working environment in the heart of Shoreditch, with ample opportunity for training and personal development. If this sounds like an exciting opportunity and you share our passion for data and stories, we look forward to hearing from you.