Practical Marketplace Optimization at Uber Using Causally-Informed Machine Learning

TL;DR

This paper presents a comprehensive machine learning and optimization framework for Uber's marketplace, utilizing causally-informed models and advanced optimization techniques to improve budget allocation efficiency for incentives and promotions.

Contribution

It introduces a novel end-to-end system combining deep learning estimators and tensor B-Spline regression for high-dimensional optimization in marketplace management.

Findings

Enhanced resource allocation efficiency at Uber.

State-of-the-art deep learning estimators for causal inference.

Effective high-dimensional optimization using ADMM and convex methods.

Abstract

Budget allocation of marketplace levers, such as incentives for drivers and promotions for riders, has long been a technical and business challenge at Uber; understanding lever budget changes' impact and estimating cost efficiency to achieve predefined budgets is crucial, with the goal of optimal allocations that maximize business value; we introduce an end-to-end machine learning and optimization procedure to automate budget decision-making for cities, relying on feature store, model training and serving, optimizers, and backtesting; proposing state-of-the-art deep learning (DL) estimator based on S-Learner and a novel tensor B-Spline regression model, we solve high-dimensional optimization with ADMM and primal-dual interior point convex optimization, substantially improving Uber's resource allocation efficiency.