Skip to content
View AtharvaPatil-Data's full-sized avatar
1 follower · 1 following
  • Dublin, Ireland

Achievements

Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Arctic Code Vault Contributor

Block or report AtharvaPatil-Data

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AtharvaPatil-Data/README.md

Typing intro

LinkedIn Email

📌 About Me

🎓 MSc in Data Analytics (Dublin City University)
🧰 Building Data Analytics and Data Engineering projects that deliver measurable business impact
🇮🇪 Based in Ireland — targeting Data Analyst & Data Engineer roles
🧭 Currently learning Airflow • Spark • Azure Databricks

🛠 Skills

Programming Languages


Python
SQL

Data Analysis & Machine Learning


Pandas
NumPy
TensorFlow
Scikit-Learn

Data Engineering & Cloud


Azure
Databricks
Airflow

Data Visualisation


Power BI		 Power Automate
Tableau		 Excel

Other Tools


GitHub
Google Colab
VS Code

🚀 Projects

📊 Diabetic Retinopathy Cascade Classification

A two-stage cascaded deep learning framework using ResNet50 for accurate early and advanced diabetic retinopathy detection, trained on APTOS 2019 and Diabetic Retinopathy Resized datasets.
Tech: Python, TensorFlow, Pandas, NumPy
🔗 View Repository

💳 Loan Defaulter Risk Model

Machine learning model to predict loan default risk using borrower profiles, credit history, and financial features.
Tech: Python, scikit-learn, imbalanced-learn, EDA
🔗 View Repository

📈 Flight Traffic Visualization

Visualizing busiest airline routes (2015–2019) using Python + Tableau.
Tech: Tableau, Pandas, Matplotlib
🔗 View Repository

🛒 E-commerce Product Categorization

Hierarchical e-commerce product categorization using TF-IDF, SMOTE, and an LR/RF/LightGBM ensemble.
Tech: Python, scikit-learn, LightGBM
🔗 View Repository

📈 Impact Snapshots

  • 📌 0.99 recall on defaulters → fewer missed high-risk customers
  • ⚡ Automated cleaning scripts → ~40% faster preprocessing
  • 📊 Executive-ready dashboards for actionable decisions

Pinned Loading

  1. AtharvaPatil-Data AtharvaPatil-Data Public

  2. Azure-Databricks-ETL-Loan-Pipeline Azure-Databricks-ETL-Loan-Pipeline Public

    Cloud ETL pipeline for LendingClub 2018Q4 loan data using Azure Databricks (Spark), ADLS Gen2, and Azure SQL. Includes notebooks, PySpark modules, and SQL scripts.

  3. Flight-Traffic-Visualization Flight-Traffic-Visualization Public

    Visualizing busiest airline routes (2015–2019) using Python + Tableau.

    Jupyter Notebook

  4. Loan-defaulter-risk-model Loan-defaulter-risk-model Public

    Machine learning model to predict loan default risk using borrower profiles, credit history, and financial features.

    Jupyter Notebook

  5. Ecommerce-Product-Categorization Ecommerce-Product-Categorization Public

    Hierarchical e‑commerce product categorization using TF‑IDF, SMOTE, and an LR/RF/LightGBM ensemble (top‑level) and Ridge (bottom‑level).

    Jupyter Notebook

  6. Diabetic-Retinopathy-Cascade-Classification Diabetic-Retinopathy-Cascade-Classification Public

    A two-stage cascaded deep learning framework using ResNet50 for accurate early and advanced diabetic retinopathy detection, trained on APTOS 2019 and Diabetic Retinopathy Resized datasets.

    Jupyter Notebook