Welcome to Advtrix Learning, a comprehensive repository of AI-driven solutions, machine learning models, automation pipelines, and an interactive Streamlit app developedby applying the knowledge and skills gained during my Advtrix Internship experience, into a practical, production-ready application.
This repository delivers production-ready implementations for:
✅ Lead Scoring Model
Predicts the likelihood of lead conversion to optimize sales outreach.
✅ Customer Segmentation
Clusters customers based on behavioral and demographic data to enable personalized marketing strategies.
✅ Trend Forecasting
Applies time series models for predicting marketing and sales trends.
✅ Churn and Marketing Analysis
A unified analysis framework for customer churn, marketing spend impact, predictive modeling, and customer clustering.
✅ Terrag AI (Streamlit App)
An AI-powered interactive analytics app built with Streamlit for data exploration, lead scoring, segmentation, forecasting, and chat-based data insights.
✅ Automation Scripts
Automated workflows for data processing, generation, and analysis.
advtrix-learning/
│
├── notebooks/ # ML & data analysis notebooks
│ ├── data/ # Datasets for notebooks
│ ├── 01_lead_scoring_model.ipynb
│ ├── 02_customer_segmentation.ipynb
│ ├── 03_trend_forecasting.ipynb
│ └── 04_churn_and_marketing_analysis.ipynb
│
├── streamlit_app/ # Terrag AI - Streamlit app for data analytics
├── automation/ # Automation scripts for data generation & cleaning
├── requirements.txt # Python dependencies
├── .gitignore # Git ignored files
└── README.md # Project documentation
🔔 Note: All datasets are stored under
notebooks/data/.
- Python: Core programming language
- Scikit-learn, XGBoost, Prophet: Machine Learning & Forecasting
- Streamlit: Interactive UI for Terrag AI
- Pandas, NumPy, Matplotlib, Altair: Data processing and visualization
- GitHub: Version control and collaboration
git clone https://github.com/MuhammadTahaNasir/advtrix-learning.git
cd advtrix-learning
pip install -r requirements.txtcd streamlit_app
streamlit run app.pyLaunch Jupyter and navigate to the notebooks/ folder:
jupyter notebookAll datasets (CSV files) are available under:
notebooks/data/
We welcome contributions! Fork the repository, submit PRs, or raise issues to collaborate.
Muhammad Taha Nasir
🤖 AI Engineer
💻 Full Stack Developer