This blog post shares the author's experiences as a new Data Scientist at Lyft, detailing their work on the Rider Experience Score (RES) tool that measures the long-term effects of rider experiences on retention. The piece discusses the challenges of causal inference in data science, the methodology used to improve the RES tool, and personal insights gained during the project. The emphasis is on leveraging advanced statistical techniques such as AIPW to generate reliable estimates, reflecting on the journey of adapting to a new role and the collaborative environment at Lyft.