Data Scientist (Forecasting)
Posted Updated
Summary
Data Scientist on PlayStation's CLV team in London, building machine-learning models (churn prediction, purchase propensity, CLV, recommendations) over large-scale player behavioural and transactional data to drive engagement and monetisation. Core stack: Python, SQL, and PySpark, with exposure to MLOps and advanced modelling.
- At PlayStation, Data Science plays a critical role in shaping how we invest in, retain, and delight our global player base. The CLV team focuses on understanding player behaviour and driving more effective engagement across the player lifecycle — from acquisition and onboarding through to retention, monetisation, and long-term value
- As a Data Scientist, you will develop models and insights that help drive more personalised player experiences and inform commercial and product decisions at scale. You will work in cross-functional teams to translate player behaviour into actionable strategies that drive measurable improvements in player engagement and value
- This role is ideal for an individual who is comfortable owning problems end-to-end — from framing and modelling through to delivering impact — and partnering with stakeholders to support data-informed decision-making
- Own the development and delivery of machine learning models for use cases such as churn prediction, purchase propensity, store recommendations, customer lifetime value
- Translate business problems into modelling approaches, selecting appropriate methods and features to deliver measurable impact
- Work with large-scale behavioural and transactional data to uncover patterns and opportunities for player growth and engagement
- Collaborate within cross-functional teams, including engineering, product, and commercial stakeholders, to ensure solutions are robust, scalable, and aligned with business needs
- Partner with stakeholders across commercial, finance, and lifecycle teams to support decision-making with data-driven insights
- Clearly communicate findings and recommendations to both technical and non-technical audiences
- Develop and expand your understanding of more advanced modelling approaches (e.g. deep learning and sequence-based methods) as part of solving increasingly complex problems
- Solid understanding of machine learning techniques (e.g. regression, tree-based models, clustering) and when to apply them, including how to refine and tune them for real-world problems
- You’re curious, analytical, and a strong problem-solver, with a structured approach to tackling business problems. You bring strong foundations in modelling and data manipulation, and are motivated by applying these to impactful, commercial problems
- Awareness of modern machine learning approaches (e.g. embeddings, sequence models, deep learning) and interest in applying them to real-world problems
- Proficiency in Python and SQL, and familiarity with common data science and ML libraries
- Experience building predictive models (e.g. churn, propensity, segmentation, or value modelling) in a commercial setting
- Ability to independently take a problem from definition through to solution and delivery, demonstrating initiative and ownership
- A strong academic background, typically a Master’s or Ph.D. in a quantitative or technical field (e.g. Mathematics, Statistics, Computer Science)
- Strong communication and collaboration skills, with the ability to clearly articulate insights and work effectively with cross-functional stakeholders
- Experience working with large datasets to generate actionable insights
- Familiarity with production environments, MLOps, or data pipelines
- Experience working with large-scale data using PySpark or equivalent distributed data processing tools
- Experience in gaming, e-commerce, or subscription-based products