No abstract

Ride-hailing services such as Lyft, Uber, and Cabify operate through smartphone apps and are a popular and growing mobility option in cities around the world. These companies can adjust their fares in real time using dynamic algorithms to balance the needs of drivers and riders, but it is still scarcely known how prices evolve at any given time. This research analyzes ride-hailing fares before and during the COVID-19 pandemic, focusing on applications of time series forecasting and machine learning models that may be useful for transport policy purposes. The Lyft Application Programming Interface was used to collect data on Lyft ride supply in Atlanta and Boston over 2 years (2019 and 2020). The Facebook Prophet model was used for long-term prediction to analyze the trends and global evolution of Lyft fares, while the Random Forest model was used for short-term prediction of ride-hailing fares. The results indicate that ride-hailing fares are affected during the COVID-19 pandemic, with values in the year 2020 being lower than those predicted by the models. The effects of fare peaks, uncontrollable events, and the impact of COVID-19 cases are also investigated. This study comes up with crucial policy recommendations for the ride-hailing market to better understand, regulate and integrate these services.

No abstract

No abstract

App-based ride-hailing mobility services are becoming increasingly popular in cities worldwide. However, key drivers explaining the balance between supply and demand to set final prices remain to a considerable extent unknown. This research intends to understand and predict the behavior of ride-hailing fares by employing statistical and supervised machine learning approaches (such as Linear Regression, Decision Tree, and Random Forest). The data used for model calibration correspond to a ten-month period and were downloaded from the Uber Application Programming Interface for the city of Madrid. The findings reveal that the Random Forest model is the most appropriate for this type of prediction, having the best performance metrics. To further understand the patterns of the prediction errors, the unsupervised technique of cluster analysis (using the k-means clustering method) was applied to explore the variation of the discrepancy between Uber fares predictions and observed values. The analysis identified a small share of observations with high prediction errors (only 1.96%), which are caused by unexpected surges due to imbalances between supply and demand (usually occurring at major events, peak times, weekends, holidays, or when there is a taxi strike). This study helps policymakers understand pricing, demand for services, and pricing schemes in the ride-hailing market.