Data Science

Data scientists build computer vision and natural language processing applications with internal tooling allowing scientists to gather, label data, train and deploy the models globally.

Fraud (Platform) Capturing credit card fraud is an uphill battle, as fraudsters constantly adapt and use stolen credit cards to find ways to get free rides. However, this team’s anti-fraud engine and machine learning models can capture such instances quickly, keeping costs down for honest users. Rentals As Bolt is a micromobility provider offering scooter and e-bike rentals across Europe, this opens up a variety of interesting technical challenges. This diverse team comprises IoT specialists, mathematical optimisation gurus, and deep learning enthusiasts. Tools & Workflows (Platform) This team optimises different user flows inside Bolt, focusing on automating the user experience. Whether helping our Customer Support team handle incoming user requests more efficiently or enabling our mapping specialists to improve routes and maps, this team has the right tools. Identity & Trust (Platform) This team’s main product is the Verification Platform, which they use to verify the identity of Bolt users and driver partners by checking the data from their documents. Afterwards, the team matches the person's face to the document and ensures that both the face and the document are first-hand captures belonging to the real person. Delivery This team owns many projects that use ride-hailing elements, such as dynamic pricing, dispatch optimisation, travel and cooking time prediction, and user food recommendations. Geo (Platform) This team focuses on enhancing map-related functionalities, employing machine learning to improve navigation and location services Campaigns (Ride-hailing) This team optimises global campaign budgets at micro (user) and macro (market) levels. On a micro level, they work on LTV, retention, churn modelling, and developing novel campaign targeting methods. Long-term market modelling for investment strategy determines the macro-level spend optimisation. Here, they deal extensively with multivariate time series forecasting of various marketplace and financial indicators. Marketplace (Ride-hailing) This team's main objective is optimising ride-hailing marketplace efficiency. Their flagship product is dynamic pricing, which balances demand and supply. Another focus area is order dispatching. These algorithms maximise order completion rates over different rider and driver matches. In addition, they work on research topics such as agent-based marketplace simulation, structural economic modelling, and causal inference that help them test, validate, and explore new optimisation areas.