Dataset

Data Information

Real-world last-mile delivery datasets are crucial for research in logistics, supply chain management, and spatio-temporal data mining. Despite many algorithms developed to date, no widely accepted, last-mile delivery dataset exists to support research in this field. The first last-mile delivery dataset with millions of packages from the industry. It has three unique characteristics: (1) Large-scale. It involves 10,677k packages of 21k couriers over 6 months of real-world operation. (2) Comprehensive information. It offers original package information, such as its location and time requirements, as well as task-event information, which records when and where the courier is while events such as task-accept and task-finish events happen. (3) Diversity. The dataset includes data from various scenarios, including package pick-up and delivery, and from multiple cities, each with its unique spatio-temporal patterns due to their distinct characteristics such as populations. We verify LaDe on three tasks by running several classical baseline models per task. We believe that large-scale, comprehensive, diverse features can offer unparalleled opportunities to researchers in the supply chain community, data mining community, and beyond.

This dataset contains comprehensive, large-scale data from real-world last-mile delivery operations, including:

1. Package Information: Location, time requirements, and delivery details for over 10 million packages.

2. Task-Event Information: Detailed logs of courier events, such as task acceptance and completion, along with GPS data.

3. Courier Information: Data on over 21,000 couriers across various cities with diverse geographical and operational conditions.

The dataset spans six months and includes data from cities like Shanghai, Hangzhou, and Jilin, each with unique logistical challenges.

This dataset can support BI-driven insights through dashboard visualizations and enable advanced ML tasks like spatio-temporal forecasting.

Metadata of Delivery Dataset

Data field	Description	Unit/format
Package information
package_id	Unique identifier of each package	Id
Stop information
lng/lat	Coordinates of each stop	Float
city	City	String
region_id	Id of the region	Id
aoi_id	Id of the AOI	Id
aoi_type	Type of the AOI	Categorical
Courier Information
courier_id	Id of the courier	Id
Task-event Information
accept_time	The time when the courier accepts the task	Time
accept_gps_time	The time of the GPS point whose time is the closest to accept time	Time
accept_gps_lng/accept_gps_lat	Coordinates when the courier accepts the task	Float
delivery_time	The time when the courier finishes delivering the task	Time
delivery_gps_time	The time of the GPS point whose time is the closest to the delivery time	Time
delivery_gps_lng/delivery_gps_lat	Coordinates when the courier finishes the task	Float
Context information
ds	The date of the package delivery	Date