How E‑Scooter Trips Vary by Time, Weather and Neighborhood

The study looks at when and where people use shared electric scooters in Kelowna, Canada. Researchers used a special statistical tool called a zero‑inflated negative binomial model to handle lots of empty records. The method splits the data into two parts: one that explains why some areas see no trips at all, and another that predicts how many rides happen when there are any. Other models were tried too, but the zero‑inflated negative binomial gave the best fit. The results show that scooter use jumps in the summer and on weekday afternoons, and it drops sharply when rain falls.Areas with many cycle paths, mixed land uses, city centers, lower ground levels and neighborhoods full of hotels or young people see more trips. The part of the model that deals with zero‑trip areas matches these patterns, giving extra confidence in the findings. A separate set of data was used to test the model’s predictions, and it performed well enough for practical use. These insights help city planners decide where to place scooters, how many to keep in stock, and when to promote their use.