Skip to content
View aniket252005's full-sized avatar
🎯
Focusing
🎯
Focusing
3 followers · 3 following

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull SharkAchievement: Quickdraw

Highlights

  • Pro

Block or report aniket252005

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
aniket252005/README.md

Aniket Pandey

Data Scientist & ML Engineer

Building ML systems that are deployed, explainable, and production-ready.

LinkedIn Portfolio Email Hugging Face

🎓 Final-year B.Tech CS (Data Science) · RAIT, Navi Mumbai  |  📍 Mumbai, India

🚀 Deployed Projects

🫁 PneumoScan AI

Chest X-ray Pneumonia Detection

AUC F1 FNR

Fine-tuned EfficientNet-B4 on 5,856 chest X-rays with Grad-CAM explainability. Reduced false negatives from 22% → 7% using Focal Loss + WeightedRandomSampler.

PyTorch EfficientNet-B4 Grad-CAM Streamlit

Live Demo Code

📉 Customer Churn Prediction

End-to-End ML API · Live on Render

AUC Recall Latency

XGBoost pipeline with SMOTE, SHAP explainability, and Flask REST API supporting real-time and batch inference.

XGBoost Flask SHAP Power BI SMOTE

Live Demo Code

🛒 Walmart Sales Forecasting

Demand Forecasting & Inventory Optimizer

MAPE Baseline Records

Benchmarked 5 models on 400K+ records. Automated EOQ, safety stock & reorder alerts. Self-service Streamlit dashboard.

XGBoost Prophet ARIMA Streamlit

Live Demo Code

📊 Numbers That Matter


Metric Value
🏥 Medical AI AUC 0.9622
📉 Churn AUC-ROC 0.84
🛒 Forecast MAPE 5.9%
📦 Records Processed 400K+
🏅 Certifications 6
🚀 Live Deployments 3

🛠 Tech Stack

Languages   Python SQL

ML / AI   Scikit-learn XGBoost Regression Classification Clustering

Deep Learning   PyTorch CNN Transfer Learning

Data   Pandas NumPy EDA Feature Engineering Data Cleaning

Visualisation   Power BI Matplotlib Seaborn Streamlit

Deployment   Flask REST API Render Hugging Face Spaces Streamlit Cloud

Tools   Jupyter Notebook Git & GitHub VS Code

📜 Certifications

Certificate Issuer
🏅 IBM Data Science Professional Certificate IBM / Coursera
🏅 Machine Learning Specialization DeepLearning.AI / Coursera
🏅 Introduction to Neural Networks with PyTorch IBM / Coursera
🏅 Convolutional Neural Networks (CNN) DeepLearning.AI / Coursera
🏅 CS50P: Introduction to Programming with Python Harvard / edX
🏅 Power BI for Beginners Simplilearn

📊 GitHub Stats

Pinned Loading

  1. customer-churn-prediction customer-churn-prediction Public

    End-to-end customer churn prediction with XGBoost, SHAP, Power BI & Flask API — deployed on Render

    Jupyter Notebook 2

  2. walmart-sales-forecasting-inventory-optimizer walmart-sales-forecasting-inventory-optimizer Public

    End-to-end ML system predicting Walmart product demand (30–90 days) using ARIMA & Prophet, with inventory optimization (Safety Stock, ROP, EOQ) and an interactive Streamlit dashboard.

    Python

  3. pneumoscan-ai pneumoscan-ai Public

    Chest X-ray pneumonia detection using EfficientNet-B4 · Grad-CAM explainability · Streamlit UI · Deployed on Hugging Face Spaces · AUC 0.9622

    Python