This repository contains a Jupyter Notebook that performs linear regression analysis on an E-commerce dataset predicting the valued customers who will most likely buy premium/ yearly subscriptions.
- Customer Engagement: Higher engagement on the app and website correlates with increased spending. This insight can drive investment in enhancing user experience on these platforms.
- Membership Length: Longer membership is associated with higher yearly spending, suggesting retention strategies can boost revenue. -Targeted Marketing: Identifying high-value customer segments helps tailor marketing efforts and promotions to maximize ROI.
- Programming Language: Python
- Libraries: pandas, numpy, matplotlib, seaborn, scikit-learn
- Data Analysis: Data cleaning, preprocessing, exploratory data analysis (EDA)
- Machine Learning: Linear regression model building and evaluation
- Visualization: Data visualization to derive business insights using Matplotlib and Seaborn
The EDA process involved visualizing relationships between various features in the dataset to gain insights into customer behavior.
We used a joint plot to visualize the relationship between the time customers spend on the website and the amount they spend yearly.
- Model Building: Built a linear regression model to predict the purchase amount based on customer behavior and time spent on the app/website.
- Model Evaluation: Evaluated the model using Mean squared and Mean Absolute Error (MAE) metrics.
- Time Spent on Website vs. Yearly Amount Spent:
This analysis showcases the ability to leverage linear regression to derive meaningful business insights and drive strategic decisions. The predictive model and findings can help businesses optimize their customer engagement and marketing strategies to enhance revenue.