You are currently viewing Data-driven Analytics Support for E-commerce

Data-driven Analytics Support for E-commerce

This post details how to develop data-driven analytics support for e-commerce. E-Commerce is a fast-growing and highly competitive space. Businesses need to continue testing and iterating to improve business operations, stand out from the competition and ensure that it is moving in the right direction.

The GitHub repository has code for a web application that tracks multiple metrics that can help the businesses to measure their performance against objectives and the overall health. The application is divided into:

1. Key Performance Indicators (KPIs) e.g., Monthly Revenue, Monthly Growth Rate, Average Order Count.

2. Customer Retention / Churn Rate.

3. Visualize Customer Journey through Sankey Diagram.

4. Customer Segmentation using RFM (Recency – Frequency – Monetary Value) Clustering.

5. Customer Acquisition Cost

6. Market Basket Optimization

7. Customer Funnel Analysis

8. Animated Bubble Plot

Bubble plot

We have generated this showcase of what we can help our clients with by using the data from Olist, the largest department store in Brazilian marketplaces. Olist connects small businesses from all over Brazil to channels without hassle and with a single contract. Those merchants are able to sell their products through the Olist Store and ship them directly to the customers using Olist logistics partners.

The dataset has information of 100k orders from 2016 to 2018 made at multiple marketplaces in Brazil. Its features allow viewing an order from multiple dimensions: from order status, price, payment and freight performance to customer location, geolocation, product attributes and finally reviews written by customers.

The application is developed using:

  1. Python
  2. Plotly
  3. Streamlit

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.