Rachel Lim is an urban data scientist who believes data can make cities more liveable, sustainable, and equitable. Her path into the field began with a degree in geography and continued with a master’s degree in urban data science, giving her a rare perspective that pairs a qualitative understanding of how cities work with rigorous quantitative analysis. Today she applies that blend to transport planning and placemaking, always with an eye on real operational impact.

In her work, Rachel draws on a wide range of urban data sources: GPS traces, sensor feeds, fare card systems, ride-hailing logs, and computer vision for analysing passenger flow. These feed into travel demand forecasting, real-time monitoring, and operational responses such as event analytics for F1 races, traffic marshals, and recovery services. She is equally comfortable with the data engineering realities behind those insights, including Kafka, Apache Spark, real-time APIs, data pipelines, warehousing, journey logic, fare computation, and data quality management.

Rachel also keeps a close eye on emerging tools, exploring how generative AI, natural-language access, and text-to-SQL architectures can make transport data more accessible, alongside synthetic data and privacy practices for publishing masked datasets. A strong believer in hands-on learning, she often points to public datasets, such as Singapore’s parking and taxi data, as an excellent starting point for anyone who wants to use data to build better cities.