🚀 Featured Project: Telecom Customer Usage Analytics Dashboard

📡Live App

Live App: https://denis0242-telecom-analysis-app-odjz0z.streamlit.app

GitHub: https://github.com/Denis0242/Telecom_Analysis

---

📡 Telecom Customer Usage Analytics Dashboard

An end-to-end telecom analytics project using Python and Streamlit for data cleaning, exploratory data analysis (EDA), KPI development, behavioral segmentation, and interactive dashboards—simulating Product Data Analyst workflows such as user behavior analysis, metric tracking, and data-driven decision-making.

---

📌 Overview

This project analyzes telecom customer behavior, usage patterns, experience indicators, and satisfaction-related metrics to generate actionable business insights. It demonstrates how raw telecom data can be transformed into stakeholder-friendly dashboards and decision-support analytics.

The repository includes a Streamlit app, analysis notebooks, Python scripts, and supporting datasets for a full workflow from raw data to interactive reporting.

---

🎯 Business Problem

Telecom companies generate large volumes of customer usage data across sessions, devices, apps, and service interactions. Without proper analysis:

• customer behavior is difficult to understand
• high-value and high-usage segments remain hidden
• experience and satisfaction issues go unnoticed
• product and operational decisions rely on assumptions instead of evidence

This project addresses those challenges by analyzing engagement, usage, experience, and satisfaction patterns in a structured, business-focused way.

---

🔍 Product Analytics Focus

• User behavior analysis
• KPI tracking and performance monitoring
• Trend and pattern identification
• Data-driven decision support

---

📊 Key Features

• Data cleaning and exploratory data analysis (EDA)
• Customer usage and engagement analysis
• Application-level usage analysis
• Behavioral segmentation using clustering
• Experience and satisfaction analysis
• Interactive dashboard built with Streamlit
• Business-readable KPI and trend reporting

---

🧠 Analytical Approach

This project follows an end-to-end analytics workflow:

• cleaned and structured telecom datasets for analysis
• explored customer behavior across sessions, duration, traffic, and app usage
• evaluated usage differences across categories such as YouTube, Google, Netflix, Email, Gaming, and Social Media
• analyzed engagement patterns and outliers
• applied clustering to identify meaningful user segments
• translated findings into an interactive dashboard for stakeholder use

---

📈 Analysis Modules

1. User Overview Analysis

• dataset quality checks
• missing value analysis
• handset manufacturer and handset type exploration
• user and session distribution
• overall usage patterns

2. User Engagement Analysis

• sessions per user
• total duration per user
• total traffic per user
• top users by usage
• outlier detection
• engagement segmentation

3. Experience Analysis

• service quality indicators
• latency and reliability metrics
• friction analysis
• user experience scoring

4. Satisfaction Analysis

• satisfaction-related metrics
• churn and retention storytelling
• satisfaction driver analysis

---

📊 Product Metrics & Impact

• Defined KPIs to measure performance such as engagement, usage intensity, and satisfaction indicators
• Identified trends and behavioral patterns in customer data
• Highlighted opportunities to improve customer experience and operational performance
• Enabled data-driven decision-making through actionable insights

Project-Specific Impact

• Analyzed user behavior across sessions, devices, and apps
• Identified high-usage segments for optimization
• Supported product and operational improvements
• Demonstrated how segmentation can guide engagement and retention strategies

---

💼 Business Impact

• Improves visibility into customer usage behavior
• Helps identify valuable and highly engaged customer segments
• Supports data-driven product and operational decisions
• Surfaces potential experience and satisfaction issues
• Demonstrates an end-to-end analytics workflow relevant to Product Data Analyst and Data Analyst roles

---

🛠️ Tools & Technologies

• Python
• Pandas
• NumPy
• Scikit-learn
• Plotly
• Matplotlib
• Streamlit
• Jupyter Notebooks
• GitHub

---

🚀 How to Run Locally

Clone the repository
git clone https://github.com/Denis0242/Telecom_Analysis.git

Navigate into the project
cd Telecom_Analysis

Create a virtual environment
python -m venv .venv

Activate the environment on Windows
.venv\Scripts\activate

Install dependencies
pip install -r requirements.txt

Run the Streamlit app
streamlit run app.py

---

📁 Project Structure

Telecom_Analysis/
│
├── Data/ — Dataset files
├── Notebooks/ — Analysis notebooks
├── scripts/ — Helper and processing scripts
├── app.py — Main Streamlit dashboard
├── main.py — Supporting application entry logic
├── requirements.txt — Project dependencies
└── README.md — Project documentation

---

🔍 Use Case

This project demonstrates:

• Strong data cleaning and EDA skills
• Ability to build interactive dashboards using Python and Streamlit
• Experience analyzing user behavior and usage patterns
• KPI development and metric tracking for decision-making
• Behavioral segmentation using machine learning techniques
• End-to-end workflow from data to analysis to visualization

---

📌 Author

Denis Agyapong
Product Data Analyst / Data Analyst