Customer Analytics: E-commerce Logistics and Sentiment Data from USA

A collection of customer and logistics records from a USA-based international e-commerce company, published by GitHub user vishalv91 in August 2020. It focuses on operational performance and customer sentiment, though the exact record count is not specified in the source metadata. The data is structured for machine learning tasks including classification and clustering.

Use Cases

• Predicting 'on-time-delivery' status using classification algorithms like Random Forest
• Performing 'twitter-sentiment-analysis' to correlate social feedback with e-commerce metrics
• Executing 'cluster-analysis' to segment customers based on database attributes

Strengths

• Includes logistics-specific tags such as on-time-delivery
• Integrates social media sentiment via twitter-sentiment-analysis tags
• Supports multi-model benchmarking for XGBoost, Random Forest, and SVM

Limitations

• Unknown record count and schema structure
• No documentation on data collection methodology or sampling bias
• Temporal staleness with no updates for over three years

Provenance

Source

vishalv91 (GitHub)

Freshness

The dataset has not been updated since August 2020.

Geography

USA