Skip to content
View parthshelar-dev's full-sized avatar

Block or report parthshelar-dev

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
parthshelar-dev/README.md

Hi, I'm Parth 👋

🎓 Third-year B.Tech student in Artificial Intelligence & Data Science at KBTCOE, Nashik.
🤖 Building ML/AI projects and aiming for an AI/ML or Data Science internship.

🚀 Featured Projects

Stellar Population Discovery Unsupervised ML on 50,000 Gaia DR3 stars — KMeans, DBSCAN, and Agglomerative Clustering with PCA (4 components, 83.87% variance explained). Deployed as a multi-page Streamlit dashboard.

PureFlowAi Agentic AI platform for SDG 6 (Clean Water & Sanitation) — 3 specialized agents plus a cross-domain orchestrator for leak detection, water quality monitoring, and predictive maintenance. Built with n8n.

Credit Card Fraud Detection — FraudShield AI End-to-end fraud detection on the ULB Kaggle dataset. Compared Logistic Regression, Random Forest, and XGBoost with SMOTE for class imbalance; XGBoost selected for deployment (PR-AUC 0.85, ROC-AUC 0.98). SHAP explainability included. Deployed as a two-tab Streamlit app.

🛠️ Tech Stack

Python TensorFlow scikit-learn Streamlit n8n

📫 Connect

LinkedIn

Pinned Loading

  1. credit-card-fraud-detection credit-card-fraud-detection Public

    Credit Card Fraud Detection using Logistic Regression, Random Forest, XGBoost, SMOTE, and SHAP Explainability.

    Jupyter Notebook

  2. PureFlowAi PureFlowAi Public

    Agentic AI platform for SDG 6 (Clean Water & Sanitation) — 3 specialized AI agents + a cross-domain orchestrator for leak detection, water quality monitoring, and predictive maintenance. Built in n8n.

    1

  3. stellar-population-discovery stellar-population-discovery Public

    Unsupervised ML project discovering stellar populations from 50,000 Gaia DR3 stars using PCA, KMeans, DBSCAN, and Agglomerative Clustering.

    Jupyter Notebook

  4. handwritten-digit-recognizer-cnn handwritten-digit-recognizer-cnn Public

    Handwritten digit recognition using a Convolutional Neural Network (CNN) trained on the MNIST dataset.

    Jupyter Notebook