Last-mile delivery, the most expensive stage of the shipment process, has become increasingly important in online retail, raising the strategic question of whether firms should outsource it to customers via pickup stations or offer home delivery. In this paper, we examine the economic value of last-mile delivery to inform this high-stakes decision. Partnering with Cainiao, Alibaba’s logistics platform, we exploit a quasi-experiment where home delivery service was sequentially rolled out to pickup stations in 2021. A staggered difference-in-differences design reveals that home delivery significantly increases sales and customer spending on Alibaba’s retail platform. Because last-mile delivery is labor-intensive and capacity constrained, effectively allocating delivery resources is crucial. To address this challenge, we propose a novel operations-aware targeting framework that integrates causal machine learning with constrained optimization to identify and prioritize the most valuable customers. The framework incorporates both capacity and fairness constraints to maximize sales while maintaining equitable service access. We further extend it with routing optimization, enabling value-aware delivery planning that jointly considers sales uplift and spatial efficiency. We demonstrate that the resulting targeting and routing policies significantly improve revenue performance. Taken together, we show that last-mile delivery is not merely a cost center but also a revenue driver. By adopting tailored logistics strategies that balance customer needs with resource constraints, online retailers can unlock substantial value and win the last mile of e-commerce. This paper was accepted by Jeannette Song, operations management. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.03991 .