Predicting Demand for Air Taxi Urban Aviation Services using Machine Learning Algorithms

TL;DR

This study applies machine learning algorithms to predict air taxi demand in New York City, identifying key temporal and weather factors influencing urban air mobility usage with gradient boosting performing best.

Contribution

It introduces a machine learning-based demand prediction framework for urban air mobility services, comparing multiple algorithms and identifying critical predictors for demand.

Findings

Gradient boosting outperforms other MLAs in demand prediction.

Temporal factors like time of day and weekday are significant predictors.

Weather conditions such as temperature and visibility influence demand patterns.

Abstract

This research focuses on predicting the demand for air taxi urban air mobility (UAM) services during different times of the day in various geographic regions of New York City using machine learning algorithms (MLAs). Several ride-related factors (such as month of the year, day of the week and time of the day) and weather-related variables (such as temperature, weather conditions and visibility) are used as predictors for four popular MLAs, namely, logistic regression, artificial neural networks, random forests, and gradient boosting. Experimental results suggest gradient boosting to consistently provide higher prediction performance. Specific locations, certain time periods and weekdays consistently emerged as critical predictors.