Evaluating Priority Dispatch for Premium Membership in On-demand Taxi-sharing

Nozomi Yamamoto; Hiroki Sakaji; Itsuki Noda

cs.MAOct 27, 2026

Evaluating Priority Dispatch for Premium Membership in On-demand Taxi-sharing

Authors: Nozomi Yamamoto, Hiroki Sakaji, Itsuki Noda

Organizations: Hokkaido University, Sapporo 060-0808, Japan

Abstract

In this paper, we analyze the dispatch-level feasibility of introducing premium membership into an on-demand taxi-sharing service using a sequential optimal insertion method. We propose two dispatch-level methods: deadline shortening for premium users, and deadline shortening with dedicated premium vehicles. We compare them with a baseline dispatch method through SUMO-based simulations under three demand scenarios: steady uniform demand, time-varying demand with a peak period, and urban-focused demand with concentrated peak traffic. Our results show that the suitable priority mechanism depends on operating conditions and premium ratio, suggesting that condition-dependent method switching may provide premium benefits while keeping non-premium-user burden smaller for overall optimization.

Figures & tables

Figure 1: Concept of the sequential optimal insertion method.

Figure 2: Concept of the proposed dispatch methods. Shorter-Deadline recalculates the allowable deadline interval for premium requests before insertion.

Figure 3: Synthetic grid map used in the experiments.

Parameter	Value
Number of vehicles $savN$	12
Vehicle deployment interval	60 s
Average vehicle speed $v_{\mathrm{sav}}$	30 km/h
Baseline deadline slack parameter $v_{\mathrm{slowest}}$	0.1 m/s
Premium deadline slack parameter $v_{\mathrm{prem}}$	0.1, 0.3, 0.5, 0.7, 1.0 m/s
Lower-bound adjustment value $N$	600 s

Table 1: Fleet and parameter settings. All deadline terms are converted to seconds in the implementation.

Scenario	Phase	Distribution	Req./h	OD Composition
S1	off-peak	Uniform	150	All $\to$ All
S2	off-peak	Uniform	150	All $\to$ All
	peak	Uniform	300	All $\to$ All
S3	off-peak	Center-focused	$\sim$ 151	Center $\to$ Center (30%) Periph. $\to$ Center (30%) Center $\to$ Periph. (20%) Periph. $\to$ Periph. (20%)
	peak	Center-heavy	$\sim$ 300	Center $\to$ Center (40%) Periph. $\to$ Center (30%) Center $\to$ Periph. (20%) Periph. $\to$ Periph. (10%)

Table 2: Summary of Demand Scenarios (S1–S3). OD denotes an origin–destination zone pair. Approximate rates result from combining OD-specific demand streams.

Figure 4: Distribution of $\delta$ for Shorter-Deadline in scenarios with peak periods.

Figure 5: Distribution of $\delta$ for Dedicated-Fleet in the steady .

Panel of Figure 6 — Figure 6: Mean time per distance at $v_{\mathrm{prem}}=0.5$ .

Real-Time Scheduling

Real-time scheduling allocates processors, accelerators, and network resources so tasks meet timing deadlines under workload and resource constraints.

See all 30 papers

D $^3$ -Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market
May 19, 2026Taijie Chen, Rui Su, Siyuan Feng +6Diffusion-Based Planning Sequential Decision Making
University of Hong Kong · Harbin Institute of Technology · Hong Kong Polytechnic University +1
GenMatch: An End-to-End Generative Matching Framework for Micro-View Order-Dispatching in Ride-Hailing
Aug 20, 2026Chuang Liu, Yuxueqing Zhang, Tengfei Lyu +6Combinatorial Optimization
Didi Chuxing Hangzhou, China · Didi Chuxing Beijing, China · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China
EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDi
Jul 10, 2026Xu Liu, Kai Wan, Zihao LuMulti-Objective Optimization
Didichuxing Co. Ltd · Beijing, China

May 19, 2026J/K move · Enter open · S save

D $^3$ -Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market

Taijie Chen, Rui Su, Siyuan Feng, Laoming Zhang+5

University of Hong Kong · Harbin Institute of Technology · Hong Kong Polytechnic University+1

Diffusion-Based Planning Sequential Decision Making

Open paper AskPDF arXiv

Ride-hailing platforms like DiDi Chuxing operate in highly dynamic environments where balancing driver supply and passenger demand is critical. Although driver-side subsidies serve as a primary lever to align these forces and improve key KPIs like completed rides (Rides) and gross merchandise value (GMV), optimizing them in production requires simultaneously meeting three constraints: (i) responsiveness to stochastic shocks, (ii) strict subsidy-rate caps, and (iii) low-latency execution at city scale. These requirements rule out expensive per-order optimization, calling for a forward-looking, constraint-aware city-level controller for online sequential decision making. To meet these requirements, we introduce D

^3

-Subsidy (Dynamic Driver-side Diffusion-based Subsidy), a hierarchical diffusion-based framework for deployable city-wide subsidy control. To bridge the train-inference gap, D

^3

-Subsidy employs a prefix-conditioned diffusion model that samples plausible future trajectories from immutable historical observations, ensuring the training protocol aligns with the fixed-history nature of online deployment. These generated plans are then decoded by a context-conditioned inverse module into low-dimensional city-level control signals. For scalable execution, we bridge the gap between city-level planning and fine-grained dispatch via a Lagrangian-dual-derived mapping, which embeds subsidy-rate caps directly into order-driver incentives without iterative optimization. Additionally, a multi-city pretraining strategy with parameter-efficient fine-tuning enables robust transfer across heterogeneous cities. Extensive offline evaluations demonstrate that D

^3

-Subsidy improves Rides and GMV while enhancing cap compliance, and a real-world A/B test confirms significant uplift while keeping budget-related violation metrics within operational thresholds.

Abstract

Real-Time Scheduling

Explore similar work

D3^33-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market

GenMatch: An End-to-End Generative Matching Framework for Micro-View Order-Dispatching in Ride-Hailing

EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDi

D $^3$ -Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market