Website Transport for London
You’ll be responsible for the wrangling, reshaping and cleaning of structured and unstructured data, harnessing its value by making it available for use by yourself and others. You will have expertise in applying data science techniques such as machine and deep learning and are confident when it comes to evaluating their performance. You will support the Principal Data Scientist in developing solutions which will leverage these methodologies.
- Support the Principal Data Scientist in researching, testing innovative approaches and developing further if successful.
- Develop and test the methodologies created by the Data Science team and research partners on developing customer profiles based on customer travel patterns, so that TfL has rich information on behavioural patterns and passenger types that up until now are only available by manually surveying customers.
- Create new tools and algorithms based on sophisticated analyses of customer travel patterns and transport operations by analysing customer and operational data sets such as ticketing, asset and sensor data.
- Discover value from vast amounts of data to enable transport operations and planning teams to make smarter decisions against an ever-changing data landscape.
- Integrate datasets and perform analyses spanning multiple sources, including large scale unstructured data, to generate new insights that span multiple TfL services.
- Develop a set of robust data analysis methods and algorithms which can be implemented by development teams and subsequently offered to key managers within TfL and external partner organisations on a managed-service basis.
- Gain efficiencies from identifying and delivering savings from analysis for business areas through greater use of data.
- Develop and further enhance existing capability in image processing and deep learning techniques.
- Proven and detailed knowledge of data and statistical analysis tools such as R, Python (Essential)
- Ability to propose solutions to analytical problems using a data driven approach. (Essential)
- Ability to communicate complex analysis effectively, both orally and in writing, with people across the organisation and outside so that the conclusions and implications of the analysis are clear and can be understood by colleagues with a wide range of technical skills. (Essential)
- Ability to understand the business impact and strategic context of the interpretation of complex data. (Essential)
- Proven knowledge of data analysis and data science methods including:
- Probability and Statistics
- Hypothesis testing
- Predictive data modelling including machine learning
- Simulation and optimisation
- Ability to analyse complex data consisting of millions of rows and draw conclusions using new analytic approaches to business questions. (Essential)
- Ability to effectively present to senior management (Essential)
- Ability to provide clear interpretation of statistical evidence and craftsman analytics that can be understood by both technical and non-technical people. (Essential)
- Advanced analytical skills including statistics, mathematics, predictive modelling, quantitative analytics, and machine learning. (Essential)
- Ability to work in a team environment, with fellow data scientists, engineers and development teams and collaboratively to service other parts of TfL (Essential)
Qualification & Experience:
- Strong experience of using data to inform and influence business strategy and decision making. For example, where the answer will be used by heads of departments, directors to guide the business strategy. (Essential)
- Strong experience of gathering, collating, analysing and publishing data in multi – media formats, for both technical and non-technical audiences. (Essential)
- Proven knowledge of how to use data to answer business questions that drive insight (Essential).
- Proven knowledge of how to scope solutions that support data science exploration (Essential).
- Knowledge of London’s public transport industry (Desirable).
- Knowledge of relevant national and international legislation pertaining to the Government/Public Sector IT – e.g. Data Protection Act, GDPR, and Freedom of Information Act, including knowledge of basic confidentiality and data protection requirements that apply to the processing of customer information (Essential).
- Experience in working with stakeholders to define business questions and analysis for decision-making. (Essential)
- Strong experience in working with extremely large data (millions of rows) and scaling compute to provide complex quantitative analyses using often hidden, messy data (Essential)
- Experience with cloud-based services such as those provided via Microsoft Azure (Essential)
- Strong experience with image processing and deep learning techniques as well as a familiarisation with the Databricks platform (Highly Desirable)
Company: Transport for London
Vacancy Type: Full Time
Job Location: London, England
Application Deadline: N/AApply Here