Dark Mode
Porter Intra-City Delivery Time Prediction Data
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Porter is India's largest marketplace for intra-city logistics, servicing over 5 million customers and working with a wide range of restaurants to deliver items directly to people. This dataset provides the necessary historical data to train regression models, including neural networks, for estimating delivery times. By utilising features such as order details, delivery partner availability, and market conditions, the data addresses the challenge of predicting accurate delivery times to enhance customer experience and operational efficiency.
Columns
- market_id: Integer ID representing the specific market location.
- created_at: Timestamp indicating when the order was created.
- actual_delivery_time: Timestamp indicating when the order was actually delivered.
- store_primary_category: Label representing the primary category of the restaurant or store.
- order_protocol: Integer code denoting the order protocol used.
- total_items: Total number of items included in the order.
- subtotal: The subtotal monetary value of the order.
- num_distinct_items: The count of distinct items within the order.
- min_item_price: The price of the least expensive item in the order.
- max_item_price: The price of the most expensive item in the order.
- total_onshift_dashers: The number of delivery partners (dashers) on shift at the time.
- total_busy_dashers: The number of delivery partners currently busy with active deliveries.
- total_outstanding_orders: The total number of orders currently waiting to be fulfilled.
- estimated_store_to_consumer_driving_duration: The estimated driving time from the store to the consumer in seconds.
Distribution
- Format: CSV (
porter_data.csv) - Size: 15.72 MB
- Structure: 14 columns
- Records: 176,000 valid rows (100% valid, 0% missing)
Usage
- Training regression models to predict delivery duration.
- Developing Deep Learning and Neural Network applications for logistics.
- Conducting Exploratory Data Analysis (EDA) on intra-city delivery performance.
- Optimising supply chain operations by analysing driver availability versus demand.
- Data visualisation of delivery trends and market behaviours.
Coverage
- Geographic Scope: India (Intra-city logistics).
- Time Range: 21 January 2015 to 18 February 2015.
- Demographic/Sector: Intra-city logistics, specifically focusing on restaurant food delivery and driver-partner metrics.
License
Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
Who Can Use It
- Data Scientists: For building and testing predictive regression models.
- Logistics Analysts: To understand factors influencing delivery delays and driver supply-demand balance.
- Machine Learning Engineers: For training neural networks on real-world logistics data.
- Operational Managers: To gain insights into market performance and delivery efficiency.
Dataset Name Suggestions
- Porter Intra-City Delivery Time Prediction Data
- India Logistics and Supply Chain Regression Dataset
- Restaurant Order Delivery Duration Metrics
- Porter Delivery Partner and Order Analysis Set
Attributes
Original Data Source: Porter Intra-City Delivery Time Prediction Data
QUALITYLoading...