Welcome to Retail Pulse, a data analytics project designed to showcase customer purchase behavior, sales trends, and actionable business insights for a fictional retail business. This project is part of my portfolio to demonstrate skills in data cleaning, exploratory data analysis (EDA), customer segmentation, forecasting, and dashboard creation.
Retail Pulse explores a transactional dataset to answer key business questions such as:
- Who are our most valuable customers?
- What products are most popular?
- How are sales evolving over time?
- Can we forecast future sales?
- What strategies can increase retention and profitability?
Languages: Python Data Analysis: pandas, numpy Visualization: matplotlib, seaborn, Plotly Forecasting: statsmodels, Prophet (optional) Dashboard: Streamlit (in progress) Notebook Environment: Jupyter
Retail-Pulse/
- data/ Retail dataset (e.g. retail_data.csv)
- notebooks/ Jupyter notebooks (EDA, forecasting)
- eda_starter_notebook.ipynb
- reports/ Summary reports and business insights
- app/ Streamlit dashboard code
- requirements.txt Project dependencies
- README.txt This file
- Clean and preprocess raw transactional data
- Analyze sales trends over time
- Identify top-selling products and countries
- Segment customers using RFM (Recency, Frequency, Monetary)
- Visualize findings using interactive and static plots
- Dashboard for business users (in progress)
- Sales forecasting with time series models (optional)
- Top 10 Products contribute over 40% of all sales
- Repeat customers in the UK drive the majority of revenue
- Sales dips observed during holiday weeks — consider marketing campaigns to boost engagement
Author: Eric Njiraini© Date: 2025 Leader in Data | Data Analyst | Data Storyteller | Insight-Driven Thinker LinkedIn: ericnjiraini
If you like this project, feel free to connect on LinkedIn for a deeper engagement! Thanks for reading through!