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

arXiv: https://arxiv.org/abs/2408.02065 · HTML: https://mlsanity.com/paper/2408.02065/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 17 references that are in the map.
- First posted on arXiv 4 Aug 2024.

## Builds on (most cited first, 3 of 3)

- [Adapting Neural Networks for the Estimation of Treatment Effects](https://mlsanity.com/paper/1906.02120/) (2019)
- [Estimating Average Treatment Effects via Orthogonal Regularization](https://mlsanity.com/paper/2101.08490/) (2021)
- [Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising](https://mlsanity.com/paper/2006.16312/) (2020)

## Built on by (most cited first, 1 of 1)

- [Cross-Treatment Effect Estimation for Multi-Category, Multi-Valued Causal Inference via Dynamic Neural Masking](https://mlsanity.com/paper/2511.01641/) (2025)

## Abstract (arXiv)

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.