Causal machine learning improves tolling for fairer and greener traffic

Resolving the Mobility-Equity-Emissions Trilemma: A Causal Machine Learning Framework for Dynamic Tolling Policy

Machine Learning

Summary

Traffic tolling policies often face a tough choice between improving travel times, being fair to different neighborhoods, and reducing pollution. The authors introduce a new method using causal machine learning to set tolls dynamically that balance these goals better. Their approach shows that tolls can reduce delays more effectively in commercial areas while greatly benefiting residential ones without losing overall efficiency. It also cuts carbon emissions significantly and finds a reliable toll range that works well in various traffic conditions. This method was tested on realistic simulated traffic data and could help guide real-world city policies.

What this means in practice

  • For urban transportation planners: Design dynamic tolls that equally reduce traffic delays across neighborhoods while minimizing emissions.
  • For traffic management centers: Implement adaptive quota systems for tolling that maintain traffic flow benefits and fairness under varying demand.
  • For smart city technology providers: Develop toll pricing software using causal methods to balance traffic efficiency, equity, and environmental impact.$Commercial implications: Enables new intelligent tolling products that optimize fairness and emissions reduction for city governments.

Tested on simulated data.

Authors

Christian Mulomba Mukendi

Abstract

We propose a causal machine learning framework to integrate dynamic tolling for mobility, equity, and climate objectives, resolving a long-standing policy trilemma. Using Double Machine Learning, we estimate zone-type-specific treatment effects, showing that commercial zones yield nearly twice the delay reduction of residential zones. Our adaptive quota mechanism expands residential coverage 34-fold while preserving 93% of total delay savings and sustaining high return on investment. The framework delivers climate co-benefits, reducing emissions by 743.5 metric tons of CO2 (valued at 141 USD) via congestion-sensitive pricing under moderate traffic conditions with sensitivity bounds from 557.6 to 929.3 tons. Crucially, we uncover a policy-invariant toll range where performance remains robust across demand scenarios, simplifying implementation. This study reveals critical, previously unidentified insights, such as a policy-invariant toll range, that can significantly simplify real-world implementation. Validated on synthetic data mirroring real-world networks, our methodological advances lay the foundation for future public deployment.
View PDFOpen arXiv