Secure Your Ride: Real-time Matching Success Rate Prediction for Passenger-Driver Pairs

  title={Secure Your Ride: Real-time Matching Success Rate Prediction for Passenger-Driver Pairs},
  author={Yuandong Wang and Hongzhi Yin and Lian Wu and Tong Chen and Chunyang Liu},
  • Yuandong Wang, Hongzhi Yin, +2 authors Chunyang Liu
  • Published 14 September 2021
  • Computer Science
  • ArXiv
In recent years, online ride-hailing platforms, such as Uber and Didi, have become an indispensable part of urban transportation and make our lives more convenient. After a passenger is matched up with a driver by the platform, both the passenger and the driver have the freedom to simply accept or cancel a ride with one click. Hence, accurately predicting whether a passengerdriver pair is a good match, i.e., its matching success rate (MSR), turns out to be crucial for ride-hailing platforms to… Expand


Origin-Destination Matrix Prediction via Graph Convolution: a New Perspective of Passenger Demand Modeling
A unified model, Grid-Embedding based Multi-task Learning (GEML) which consists of two components focusing on spatial and temporal information respectively, designed to model the spatial mobility patterns of passengers and neighboring relationships of different areas is proposed. Expand
A Unified Framework with Multi-source Data for Predicting Passenger Demands of Ride Services
  • Yuandong Wang, Xuelian Lin, +4 authors Jie Xu
  • Computer Science
  • ACM Trans. Knowl. Discov. Data
  • 2019
This article presents a unified framework with a new combined model and a road-network-based spatial partition to leverage multi-source data and model the passenger demands from temporal, spatial, and zero-demand-area perspectives and indicates that the model outperforms baselines on both Mean Absolute Error and Root Mean Square Error. Expand
ZEST: A Hybrid Model on Predicting Passenger Demand for Chauffeured Car Service
A Zero-Grid Ensemble Spatio Temporal model to predict passenger demand with four predictors: a temporal predictor and a spatial predictor to model the influences of local and spatial factors separately, an ensemble predictor to combine the results of former two predictors comprehensively and a Zero- Grid predictor to predict zero demand areas specifically. Expand
Online Minimum Matching in Real-Time Spatial Data: Experiments and Analysis
A comprehensive experimental comparison of the representative algorithms of the OMBM problem and observes a surprising result that the simple and efficient greedy algorithm, which has been considered as the worst due to its exponential worst-case competitive ratio, is significantly more effective than other algorithms. Expand
Online mobile Micro-Task Allocation in spatial crowdsourcing
This paper identifies a more practical micro-task allocation problem, called the Global Online Micro-task Allocation in spatial crowdsourcing (GOMA) problem, and proposes a two-phase-based framework, based on which the TGOA algorithm with 1 over 4 -competitive ratio under the online random order model is presented. Expand
Two-Sided Online Micro-Task Assignment in Spatial Crowdsourcing
A two-phase-based framework is proposed, based on which the TGOA algorithm with a <inline-formula><tex-math notation="LaTeX">-competitive ratio under the random order model is presented and the average performance of Greedy is considered, which has been considered as the worst due to its unbounded competitive ratio in the worst case. Expand
The Simpler The Better: A Unified Approach to Predicting Original Taxi Demands based on Large-Scale Online Platforms
This work proposes LinUOTD, a unified linear regression model with more than 200 million dimensions of features, which outperforms popular non-linear models in accuracy and can shed insights upon other industrial large-scale spatio-temporal prediction problems. Expand
Dynamic Heterogeneous Graph Neural Network for Real-time Event Prediction
This paper proposes to use dynamically constructed heterogeneous graph for each ongoing event to encode the attributes of the event and its surroundings and proposes a multi-layer graph neural network model to learn the impact of historical actions and the surrounding environment on the current events. Expand
Next Point-of-Interest Recommendation on Resource-Constrained Mobile Devices
A novel Light Location Recommender System (LLRec) to perform next POI recommendation locally on resource-constrained mobile devices, which significantly reduces the dependency on cloud servers, thus allowing for nextPOI recommendation in a stable, cost-effective and secure way. Expand
Functional Zone Based Hierarchical Demand Prediction For Bike System Expansion
A hierarchical station bike demand predictor which analyzes bike demands from functional zone level to station level and estimates the station demand by studying the demand distributions among the stations within the same functional zone. Expand