Dark Mode
Courier Performance and Last-Mile Logistics Dataset
Retail & Consumer Behavior
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Predicting food delivery times requires a multi-faceted approach that considers logistical, environmental, and human factors. By integrating variables that reflect real-world challenges—such as variable traffic levels and specific weather phenomena—this resource enables a deeper understanding of the complexities involved in the "last mile" of food logistics. This framework captures the intersection of urban congestion, meteorological conditions, and personnel performance to provide a foundation for high-accuracy delivery speed estimation, moving beyond simple distance-based metrics to a thorough predictive model. It addresses gaps in existing industry applications by incorporating critical variables like vehicle type and detailed atmospheric descriptions to refine transport efficiency.
Columns
- ID: A unique identifier assigned to each individual delivery record for tracking purposes.
- Delivery_person_ID: A unique code used to distinguish and monitor the performance of specific delivery personnel.
- Delivery_person_Age: The age of the courier, which serves as a factor for analysing demographic trends in delivery efficiency.
- Delivery_person_Ratings: Customer feedback scores that reflect the quality of service and overall satisfaction for each delivery.
- Restaurant_latitude: The precise latitudinal coordinate of the origin point where the food is prepared.
- Restaurant_longitude: The precise longitudinal coordinate of the origin point where the food is prepared.
- Delivery_location_latitude: The exact latitudinal coordinate of the destination where the order is delivered.
- Delivery_location_longitude: The exact longitudinal coordinate of the destination where the order is delivered.
- Distance (km): The calculated physical distance between the restaurant and the delivery destination.
- Type_of_order: A classification of the food items, such as snacks, meals, drinks, or buffets, which influences preparation and packaging times.
- Type_of_vehicle: The mode of transport utilised by the courier, including motorcycles, scooters, bicycles, or electric scooters.
- Temperature: The recorded ambient temperature during the delivery process.
- Humidity: The moisture level in the air at the time of transport.
- Precipitation: The recorded level of rainfall or snowfall occurring during the delivery window.
- weather_description: Contextual details regarding atmospheric conditions, such as clear skies, haze, or storms.
- Traffic_Level: A categorised measure of road congestion, ranging from low to high.
- TARGET: The primary outcome variable representing the total delivery time in minutes.
Distribution
The information is delivered in a CSV file titled
Food_Time new.csv with a file size of approximately 1.28 MB. It contains 10,000 valid records structured across 17 columns, maintaining 100% data integrity with no reported mismatched entries. The collection is intended for annual updates to ensure the data remains relevant to changing urban logistics patterns.Usage
This resource is ideal for developing machine learning models aimed at optimising delivery logistics and improving the accuracy of estimated arrival times (ETA). It is well-suited for researchers studying the correlation between environmental factors—such as precipitation and humidity—and transport speed. Additionally, business analysts can use these records to benchmark courier performance and evaluate how different vehicle types navigate various levels of traffic congestion.
Coverage
The scope of the records provides precise geographical details via latitude and longitude coordinates for both pickup and drop-off locations. It encompasses a wide range of human factors, including courier age and customer ratings, alongside environmental metrics that capture diverse weather conditions and traffic intensities. The data represents a varied look at food-tech logistics, covering multiple order types and transport modes within an urban context.
License
CC0: Public Domain
Who Can Use It
Logistics engineers and data scientists can leverage these records to refine routing algorithms and predictive delivery frameworks. Business owners in the food-delivery sector might utilise the insights to improve customer service by providing more reliable timing. Furthermore, academic researchers in the fields of transport studies and urban planning can find this a valuable primary source for investigating the impact of weather and congestion on city-wide delivery networks.
Dataset Name Suggestions
- Urban Food Delivery Logistics and Time Prediction Index
- Multi-Factor Delivery Speed and Environmental Impact Archive
- Courier Performance and Last-Mile Logistics Dataset
- Food-Tech Predictive Framework: Traffic, Weather, and Time
- Geospatial Delivery Metrics and Speed Analysis Registry
Attributes
Original Data Source: Courier Performance and Last-Mile Logistics Dataset
QUALITYLoading...
Free
Download Dataset in CSV Format
Recommended Datasets
Loading recommendations...