See https://www.kaggle.com/datasets/olistbr/brazilian-ecommerce .

This dataset offers customer location details, providing valuable geographical context for orders placed through the Olist Store, a prominent department store operating across various Brazilian marketplaces. It encompasses real commercial data from 2016 to 2018, which has been carefully anonymised. The primary purpose is to enable insights into customer geographical distribution, which is key for market analysis and logistics planning. This dataset can be readily combined with other related Olist datasets, such as the main e-commerce order data and marketing funnel information, to unlock deeper analytical perspectives.

Columns

• customer_id: A unique identifier assigned to each individual customer transaction.
• customer_unique_id: A distinct identifier that represents a singular customer, allowing for tracking across multiple purchases.
• customer_zip_code_prefix: The initial five digits of the customer's postal code, indicating a specific geographical area or region.
• customer_city: The city in Brazil where the customer is situated.
• customer_state: The Brazilian state where the customer is located.

Distribution

The dataset is typically provided in a CSV file format, designed for ease of use and integration. While the exact row count for this specific geolocation dataset is not explicitly stated, it is a segment of a larger e-commerce dataset that includes information for 100,000 orders. This data is structured to provide geographical attributes for customer records, serving as a foundational part of a broader collection of interconnected datasets from Olist.

Usage

This dataset is an excellent resource for geographical analysis of customer bases, facilitating the optimisation of delivery routes and logistics networks, and gaining an understanding of regional market dynamics. It can be effectively employed for spatial clustering of customers, identifying areas of high customer density, and developing location-based features for machine learning models. Furthermore, it plays a vital role in feature engineering, allowing for the integration of external public geographical information to enrich existing data.

Coverage

The dataset specifically covers customer locations across Brazil, providing details on Brazilian zip codes, cities, and states. The information relates to e-commerce orders processed between 2016 and 2018 within the Olist ecosystem. It consists of genuine commercial data, with all potentially identifying company and partner names having been replaced for privacy.

License

CC-BY-SA

Who Can Use It

• Data Analysts and Data Scientists aiming to perform geographical market segmentation and develop detailed customer profiles.
• Logistics Managers seeking to enhance delivery performance, refine supply chain strategies, and improve route planning efficiency.
• Business Strategists focused on identifying new regional market opportunities and planning expansion initiatives.
• Researchers interested in studying Brazilian consumer behaviour and the impact of e-commerce on urban and regional development.

Dataset Name Suggestions

• Brazilian E-Commerce Customer Geography
• Olist Customer Location Data
• Brazil Retail Geolocation Prefixes
• E-commerce Customer Spatial Insights

Attributes

Original Data Source: Brazilian E-Commerce Public Dataset by Olist

E-Commerce Analytics for Delivery and Review Prediction

This dataset was created for a datathon project. It's a cleaned and feature-engineered version of the public Olist Brazilian E-commerce dataset, specifically prepared to predict shipping delays and customer review scores.

  Project Goals

Our project focuses on two key business problems:

Model 1 (Regression): Can we predict how delayed a shipment will be? This helps manage customer expectations proactively. Model 2… See the full description on the dataset page: https://huggingface.co/datasets/miminmoons/olist-ecommerce-for-delivery-and-review-prediction.

Dataset

This dataset was created by Ramadya Tridhana R

Contents

Please do not hesitate ask any question and thank you for olist to share with us original dataset.I just cleaned and manipulated by creating new dataset.