Machine Learning in Action: Real-World AI Projects

Welcome to my public repository — perfect for learners, practitioners, and contributors interested in exploring and applying real-world machine learning and AI techniques. These projects reflect a journey of experimentation, learning, and hands-on implementation across various domains of artificial intelligence.

⚠️ Note: This repository is an ongoing project and is continuously evolving. New AI and ML projects will be added regularly — stay tuned for updates!

What's Inside?

This repository features practical and research-driven projects in:

• Structured Exploratory Data Analysis (EDA)

  • Uncovering Trends in Netflix Content
  • Analyzing IPL Trends: Insights from 2008 to 2019

• Deep Learning and Neural Networks

  • Handwritten Character Recognition with EMNIST

• Supervised and Unsupervised Learning

  • Predict Wild Blueberry Yield | Kaggle Playground Series S3
  • Performance Analysis of Linear Models for Salary Prediction

• Natural Language Processing (NLP)

• Computer Vision

• Reinforcement Learning

• Time Series Forecasting

• MLOps and Model Deployment

Each project will be self-contained with code, documentation, and instructions.

Articles & Writing

In addition to this code repository, I actively write about data science, machine learning, and practical project workflows on platforms like Medium and Kaggle. See the full list here. These pieces complement the projects here with deeper context, theory, and lessons learned.

Repository Structure

real-world-ai-projects/
├── README.md                      # Overview of the entire repository
├── ARTICLES                       # Articles on data science, machine learning, and practical project workflows
├── LICENSE                        # Repository license and usage terms
├── project-category/              # Thematic or functional grouping of related projects
│   └── project-name/              # Individual project directory
│       ├── README.md              # Documentation specific to this project
│       ├── data/                  # Raw data files or scripts to load datasets (optional)
│       ├── source/                # Jupyter notebooks and source code for analysis and modeling
│       ├── requirements.txt       # List of Python dependencies for this project

How to Use

To run any project:

1. Navigate to the relevant folder under project-category/.
2. Review the README.md in that folder for instructions.
3. Set up your environment using the requirements.txt file.
4. Run the notebooks or Python scripts inside the source/ directory.

Projects use a variety of standard Python libraries including:

• pandas, NumPy, scikit-learn for data science
• TensorFlow and PyTorch for deep learning
• spaCy, NLTK for NLP
• OpenCV for computer vision
• Tools like Flask, FastAPI, or Streamlit for deployment (coming soon)

Roadmap

Here's what to expect in future updates:

• Baseline ML models with clean code
• Model training & evaluation pipelines
• Model deployment examples (APIs, dashboards, etc.)
• Experiment tracking and logging tools
• Mini case studies and data stories

Stay tuned and star ⭐ this repo if you'd like to follow along!

License

All projects in this repository are © 2025 Saurabh Kudesia and licensed under the MIT License. You are free to use, modify, and distribute this code, provided that proper attribution is given and the original license notice is retained. Please note that portions of the projects — such as datasets, code references, or assets — may be sourced from third-party providers and remain subject to their respective licenses and terms of use. Some icons used in this repository are provided by Font Awesome, licensed under CC BY 4.0.

Contributing

Have ideas or suggestions? Contributions are welcome!

• Open an issue for bugs or feature requests
• Fork the repo and create a pull request for contributions
• Check each project's README for contribution guidelines (if any)

Let's Connect