Dark Mode
E-commerce Delivery Prediction Data
E-commerce & Online Transactions
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
A robust dataset built on the foundation of the booming e-commerce sector, this product allows for the understanding and optimisation of customer experience. It originates from an international e-commerce company that specialises in electronic products. Leveraging advanced machine learning techniques is the key aim, allowing users to dissect the dynamics of customer interactions and product shipments to enhance overall satisfaction and operational efficiency. The ultimate goal is to generate actionable insights leading to enhanced product shipment tracking and a significant competitive advantage.
Columns
The dataset includes 12 carefully selected variables that map the customer journey:
- ID: A unique customer identifier used for precise tracking and generating personalised insights.
- Warehouse Block: Categorises the company's expansive warehouse into blocks (A through E), essential for optimising logistics and inventory management.
- Mode of Shipment: Details the shipment method used (Ship, Flight, Road), enabling analysis of delivery efficiency and customer satisfaction.
- Customer Care Calls: Records the frequency of customer inquiries, serving as an indicator of service quality. The values range from 2 to 7.
- Customer Rating: A direct measure of customer satisfaction, scaled from 1 (lowest) to 5 (highest).
- Cost of the Product: A financial metric vital for analysing pricing strategies and assessing profitability, with costs ranging from 96 to 310.
- Prior Purchases: Tracks purchase history to help in predicting future buying behaviour, with values spanning 2 to 10 purchases.
- Product Importance: Classifies products based on their handling priority (low, medium, high).
- Gender: Allows for analysis of shopping patterns and preferences across genders (Female and Male).
- Discount Offered: Examines the influence of sales discounts on volume and customer acquisition, with discounts ranging from 1 to 65.
- Weight in Grams: A critical logistical factor influencing shipping costs and chosen delivery methods, with weights ranging from 1001 to 7846 grams.
- Reached on Time: The critical outcome variable (0 or 1), indicating whether the delivery occurred within the expected timeframe, serving as a benchmark for operational efficiency.
Distribution
The dataset structure is suitable for analysis, containing 10,999 observations (rows) across 12 variables. The data is typically supplied in a CSV format. All variables are 100% valid with zero missing data points. The outcome variable, 'Reached on Time', shows that approximately 60% of deliveries successfully met their deadlines.
Usage
This data is ideal for applying machine learning models focused on classification problems, such as predicting the success rate of on-time delivery. It can be used to inspire data-driven strategies that address pressing operational questions, including:
- Investigating the correlation between customer ratings and timely deliveries.
- Assessing the effectiveness and impact of customer support operations.
- Determining the influence of product importance on delivery performance.
- Developing strategies aimed at optimising logistics and improving the overall customer journey.
Coverage
The data covers transactional and logistical information collected by an international e-commerce company specialising in electronic products. While specific geographic and precise temporal ranges are not detailed, the demographic scope includes a balanced representation across genders.
License
CC0: Public Domain
Who Can Use It
- Data Scientists and ML Engineers: For constructing predictive models designed to classify delivery success.
- Logistics and Supply Chain Analysts: To optimise the allocation of warehouse blocks and evaluate the efficiency of various shipment modes (Ship, Flight, Road).
- Customer Experience Managers: To correlate metrics like customer care calls and satisfaction ratings directly with final delivery outcomes.
Dataset Name Suggestions
- E-commerce Delivery Prediction Data
- Customer Satisfaction and Logistics Metrics
- Shipment Timeliness Analysis
- Operational Efficiency Dataset
Attributes
Original Data Source: E-commerce Delivery Prediction Data
QUALITYLoading...