Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/myself-aas/quantium_data_analytics_forage

This project analyzes retail customer chip purchasing behavior using Python, focusing on customer segmentation and key spending drivers to provide data-driven insights for strategic category management recommendations.
https://github.com/myself-aas/quantium_data_analytics_forage

data-analysis data-engineering data-science data-visualization feature-engineering forage internship-project matplotlib-pyplot numpy-library pandas-dataframe pearson-correlation python quantium-virtual-experience scipy-stats seaborn

Last synced: about 18 hours ago
JSON representation

This project analyzes retail customer chip purchasing behavior using Python, focusing on customer segmentation and key spending drivers to provide data-driven insights for strategic category management recommendations.

Awesome Lists containing this project

README 

        

# Project Title



**Quantium Data Analytics Forage Internship**



This repository contains the work I completed as part of the Quantium Data Analytics Forage Virtual Internship, where I performed an in-depth analysis of customer purchasing behavior with a focus on chips. The primary objective of this project is to provide strategic recommendations for optimizing category management, based on data-driven insights.



In this task, I used Python for data analysis, data preprocessing, and visualization. The goal is to deliver actionable insights into customer segments and their purchasing behavior, which will support recommendations for Julia, the Category Manager.

## Project Overview



The project focuses on understanding customer behavior related to chip purchasing. The task involves analyzing a dataset to identify key customer segments, purchasing trends, and other factors influencing chip purchases.



Key components of the analysis include:



- Exploratory Data Analysis (EDA)

- Data cleaning and preprocessing

- Visualization of key metrics

- Statistical modeling and hypothesis testing

- Creating actionable insights for business decision-making

## Objectives



- Analyze customer purchasing behavior based on segments.

- Identify key metrics and insights related to chip purchases.

- Derive features such as pack size and brand name.

- Provide recommendations based on findings for category review.

## Key Analysis Steps



- **Data Cleaning & Preparation:** Identifying and handling missing values, outliers, and correcting data formats.

- **Feature Engineering:** Creating new features like pack size, brand name, and other relevant metrics.

- **Exploratory Data Analysis (EDA):** Summary statistics, visualizations, and initial insights into purchasing patterns.

- **Segmentation Analysis:** Identifying distinct customer segments based on purchasing behavior.

- **Statistical Testing:** Conducting hypothesis tests to assess differences in purchasing behaviors.

- **Strategic Recommendation:** Generating actionable insights to inform Julia's category review.

- **Sales Revenue Analysis:** Understanding total sales performance across different stores.

- **Customer Behavior Insights:** Exploring customer metrics such as purchase frequency and customer retention.

- **Trial Store Evaluation:** Analyzing trial stores in comparison to control stores using metrics such as total sales, number of customers, and purchases per customer.

- **Statistical Testing:** Performing hypothesis testing to assess the significance of differences in sales between trial and control stores.

## Tools & Technologies Used



- **Jupyter Notebooks:** For documenting and presenting the analysis in an interactive manner.

- **Python:** For data analysis, preprocessing, and statistical testing.

- **Pandas:** For data manipulation and transformation.

- **Matplotlib:** For creating visualizations and charts.

- **Seaborn:** For advanced data visualization and statistical plotting.

- **SciPy.stats:** For statistical analysis and hypothesis testing.

- **NumPy:** For numerical operations and array handling.

## Deployment



**Clone the Repository:**



To deploy this project Clone the Repository



```bash

  git clone https://github.com/your-username/Quantium_Data_Analytics_Forage.git



```



**Install Required Libraries:**



The following libraries are used in this project:



- ``numpy``

- ``pandas``

- ``matplotlib``

- ``seaborn``

- ``scipy``



**Run Jupyter Notebooks:**



Navigate to the folder containing the notebooks and open them in Jupyter Lab or Jupyter Notebook:

```bash

    jupyter notebook

```

## Analysis and Results



- **Exploratory Data Analysis (EDA):** High-level summary statistics and visualizations were created to explore customer behavior across various segments.

- **Outlier Detection & Handling:** Identified and removed outliers where applicable.

- **Customer Segmentation:** Key customer segments were identified, focusing on spending behavior and the factors that influence their chip purchasing.

- **Feature Engineering:** New features such as pack size and brand were created to enhance the analysis.

- **Statistical Testing:** Hypothesis testing was conducted to evaluate significant differences in purchasing behavior.

- **Sales Performance Comparison:** A detailed comparison of sales performance in trial stores vs control stores.

- **Customer Behavior:** Insights into customer transaction frequency and average purchases.

- **Statistical Significance:** Hypothesis testing and confidence intervals to assess the impact of trial interventions.

## Key Insights



- Certain customer segments showed higher chip spending, influenced by factors such as pack size and brand preference.

- Statistical tests confirmed significant differences in purchasing behavior among customer segments, which could be leveraged to improve sales strategies.

- The analysis provides the foundation for creating personalized marketing strategies for different segments.

- Analysis of store performance indicated a significant difference in sales performance between trial and control stores.

- The trial stores showed an increase in customer engagement, with higher transaction frequency contributing to improved sales.

- Insights derived from the analysis can be leveraged to optimize store operations and marketing strategies.

## Future Work



- Further segmentations can be explored based on additional factors such as geographical location or customer demographics.

- More advanced machine learning models could be applied to predict customer behavior and optimize inventory management.

- A deeper dive into competitor data could provide further insights into purchasing trends.

- Investigate seasonality effects on sales.

- Incorporate more granular customer data for deeper insights into customer behavior.

- Extend the analysis to predict future sales using machine learning models.

## License



This project is licensed under the [MIT](https://choosealicense.com/licenses/mit/) License.



## Acknowledgements



- **Quantium** for providing the data and the opportunity to participate in this internship.

- **Forage** for organizing this virtual internship and providing valuable learning experiences.



## Authors



- [@myself-aas](https://github.com/myself-aas)