This is a Jupyter notebook/Lab exploring and analyzing online retail data.
Business Objective
Analyze the patterns of repeat customers and their contributions to overall revenue.
- Country of Origin
- How many repeat customers
- Product with most repeat customers
- Max, min, average spend repeat customers
- Minimum Spend on popular Product for repeat customers
Track the trends of popular items over time
- demand of favorite product per country
- Average spend per customer on product
- Quantity change of popular product with time
- Trendline for demand of popular product
Utilize this trending item data for product recommendations in marketing strategies.
- What the company should do to attract more repeat customersfor the best-selling product?
- The marketing strategy to improve sales in a certain country.
- How to retain market that has most demand for popular product
Predict Customer’s 3 month CLV
Product Analytics
To understand how customers engage and interact with different products.
- Which product has most sales in quantity, revenue, repeat customers?
- " " least in total sales, ""
- Product with max Identify popular and tending products
Identify repeat customers and repeat items Segment products and customers based on their key attributes using customer profile and product data Improve customer and product retention Develop marketing strategies
Customer Lifetime Value (CLV)
CLV is an important marketing metrics It measures customers' total worth to the business over the course of their lifetime relationship with the company. CLV for individual customers helps marketers in justifying their marketing budget When determining the budget for a marketing strategy, it is essential to know what the expected return will be from running a given marketing campaign. It also helps in targeting potential high-value customers. If your marketing spend for new customer acquisition exceeds the CLV, you will lose money for each acquisition so better to work with the existing customers.
Estimate CLV over the course of a certain period. 12-month CLV 24-month CLV 3-month CLV CLV can be estimated through building predictive models. Use machine learning algorithms and customers' purchase history data to build a model. In this project we will build a regression model that predicts customers' 3-month CLV
Methodology
Data Import Data Overview Data Cleaning Exploratory analysis Time series trends/analysis Customer interaction with individual products Customer interaction changes over time Model building
All this is well demonstrated.
DISCLAIMER!! CODE IS NOT ERROR PROOF