_ __ _ _ ____ _ _ _
| |/ / | | | | | _ \| | | | (_)
| ' / _ _ | | __| | ___ ___ _ __ | |_) | |__ __ _ _ __ __| |_ ____ _ _ _
| < | | | | | | / _` |/ _ \/ _ \| '_ \ | _ <| '_ \ / _` | '__/ _` \ \ /\ / / _` | | | |
| . \| |_| | | || (_| | __/ __/| |_) | | |_) | | | | (_| | | | (_| |\ V V / (_| | |_| |
|_|\_\\__,_| |_| \__,_|\___|\___| .__/ |____/|_| |_|\__,_|_| \__,_| \_/\_/ \__,_|\__, |
| | __/ |
|_| |___/
B.Tech Electrical Engineering @ IIT Delhi
Building ML systems end-to-end — from raw data to deployed models with real-world impact.
class Kuldeep(MLEngineer, SoftwareDeveloper):
"""
Building ML systems end-to-end — from raw data
to deployed models with real-world impact.
"""
def __init__(self):
self.role = "Aspiring AI/ML Engineer"
self.base = "Delhi, India"
self.degree = "B.Tech Electrical Engineering, IIT Delhi"
self.focus = ["ML Systems", "ETL Pipelines", "Production AI"]
self.status = "Open to opportunities"
def current(self):
return {
"building" : "Credit Card Fraud Detection — SHAP/LIME interpretability",
"learning" : "Advanced DSA + Digital Signal Processing",
"seeking" : "Collaboration on time-series forecasting & recommender systems",
"fun_fact" : "Junior Engineer @ Axlr8r Formula Racing — 110V Li-ion battery optimization"
}End-to-end MLOps project — hybrid ensemble model, Streamlit dashboard, SHAP/LIME explainability, and data drift detection.
- Trained on 100K+ transactions with severe class imbalance addressed via SMOTE
- Ensemble model combining deep learning layers with gradient boosting
- SHAP + LIME integration for per-prediction fraud driver explanation
- Live monitoring dashboard with Streamlit for drift detection
PyTorch XGBoost SHAP LIME SMOTE Streamlit MLOps
Personalized hybrid recommender for games using SVD + TF-IDF + ensemble methods on 230K+ reviews with a live Streamlit dashboard.
- Collaborative filtering via Singular Value Decomposition (SVD)
- Content-based layer using TF-IDF on review text and metadata
- Evaluated on Precision@K and Recall@K across cold-start and warm-user scenarios
- MongoDB backend for scalable data storage and retrieval
Collaborative Filtering SVD TF-IDF MongoDB Streamlit Pandas
NYC Uber rides analysis — time series forecasting with Prophet, Folium maps, and demand modeling.
- Spatiotemporal pattern analysis on large-scale NYC ride data
- Demand forecasting using Facebook Prophet for hourly/daily granularity
- Interactive geospatial visualizations with Folium heatmaps
- Deployed as a live Streamlit web application
Prophet Time-Series Geospatial Folium NumPy Pandas Streamlit
Languages
Machine Learning & Deep Learning
Data & Analytics
Cloud & Infrastructure
Databases & Tools
status: open to opportunities — reach out at contact@kuldeepbhardwaj.me