A Multi-class Ride-hailing Service Subsidy System Utilizing Deep Causal Networks

TL;DR

This paper presents a deep causal network approach to optimize ride-hailing subsidies, accurately estimating consumer responsiveness while addressing confounding effects to enhance market growth strategies.

Contribution

It introduces a novel lightweight causal inference system that models subsidy propensity and treatment effects simultaneously for ride-hailing services.

Findings

Effective estimation of consumer elasticity under subsidy variations

Reduced bias in uplift effect measurement

Applicable in real-time online environments

Abstract

In the ride-hailing industry, subsidies are predominantly employed to incentivize consumers to place more orders, thereby fostering market growth. Causal inference techniques are employed to estimate the consumer elasticity with different subsidy levels. However, the presence of confounding effects poses challenges in achieving an unbiased estimate of the uplift effect. We introduce a consumer subsidizing system to capture relationships between subsidy propensity and the treatment effect, which proves effective while maintaining a lightweight online environment.