Were ride-hailing fares affected by the COVID-19 pandemic? Empirical analyses in Atlanta and Boston

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.

Keywords: COVID-19; Dynamic Pricing; Machine Learning; Ride-Hailing; Time Series Forecasting; Transport Policy.

Fig. 1

Evolution of COVID-19 cases during 2020 (Authors’ work based on the Fulton County Board of Health Epidemiology Division, , and the Boston Public Health Commission, 2022)

Fig. 2

Atlanta city and selection of the ODs of the requested rides (Authors’ work using a GIS tool)

Fig. 3

Boston city and selection of the ODs of the requested rides (Authors’ work using a GIS tool)

Fig. 4

Average monthly fares for Lyft, before the COVID-19 pandemic (blue line) and during the COVID-19 pandemic (orange line)

Fig. 5

Boxplot of the average monthly fares for Lyft

Fig. 6

Training (in black) and testing (in blue) of the Facebook Prophet model in the base year (2019)

Fig. 7

Estimated average monthly fares for Lyft in comparison to 2020

Fig. 8

Predictions for each possible route for the year 2019

Fig. 9

Predictions for each possible route for the year 2020

Fig. 10

Seasonal decomposition using moving averages in Atlanta in the year 2019

Fig. 11

Seasonal decomposition using moving averages in Atlanta in the year 2020

Fig. 12

Seasonal decomposition using moving averages in Boston in the year 2019

Fig. 13

Seasonal decomposition using moving averages in Boston in the year 2020