Machine Learning Data Science

CHETAN DNYANESHWAR KHARKAR

********@***.*** 774-***-**** github.com/chetankharkar21 chetankharkar.netlify.app Education

Master of Science in Data Science (Worcester Polytechnic Institute (WPI)) 2024 – 2026 Worcester, USA

•Coursework : Big data, Deep learning, Statistical Methods, Business Intelligence, Natural Language Processing Bachelor of Engineering in Electronics and Telecommunication (SPPU) 2019 – 2023 Pune, India

•Honors: Artificial Intelligence & Machine Learning Specialization

•Coursework : Database Management System, Cloud computing, Machine Learning, Computational Statistics Professional Experience

Data Analyst (Worcester Polytechnic Institute - Facilities Department) present Worcester, USA

•Analyzed 10,000+ work orders monthly, optimizing resources and reducing budget variances by 15%

•Designed and maintained interactive dashboards using Tableau and Power BI, improving data-driven decision-making for facilities management

•Conducted anomaly detection on utility bills, identifying abnormal electricity consumption in dorms, leading to corrective actions and cost savings

•Developed predictive models with Python and Matplotlib/Plotly to improve work order scheduling Graduate Engineer Trainee ( Vodafone idea limited ) Sep 2023 – Jul 2024 Pune, India

•Leveraged advanced Excel and Python for efficient data analysis and visualization, improving decision-making workflows

•Created dynamic Excel reports to visualize network performance KPIs, enhancing operational insights for senior management Data Science intern (Stacklab.in) May 2023 – Aug 2023 Pune, India

• Designed a Naive Bayes text classifier integrated with TF-IDF, boosting classification accuracy to 88%

• Led a team of 5 interns, fostering collaboration and delivering high-quality data-driven solutions Projects

Health Informatics Research: NLP for Clinical Notes (WPI) Sep 2024 – present

• Developed a deep learning pipeline using PyTorch for clinical note summarization, improving interpretability by 35%

• Applied LLM techniques to extract critical health indicators, achieving a precision score of 0.91 in medical data analysis

• Automated text preprocessing using NLTK, reducing pipeline runtime by 25% Kidney Cancer Classification System(WPI) Dec 2024

•Developed an end-to-end Deep Learning pipeline for kidney CT scan classification using TensorFlow, DVC, MLflow, and Flask for the web interface

•Deployed a scalable solution on AWS with Docker and GitHub Actions, enabling real-time cancer detection

•Streamlined model tracking, version control, and CI/CD for robust and efficient deployment NYC Taxi Data Analysis(WPI) Nov 2024

•Analyzed NYC taxi data (1.4M records) to identify ride trends, hotspots, and clustering patterns using Python libraries like Pandas, Folium, and Matplotlib

•Applied PyTorch neural network model for trip duration prediction, achieving 67.7% variance explanation, and enhanced results using Optuna for hyperparameter tuning

•Conducted feature engineering (e.g., Haversine distance, speed) and deployed a LightGBM model, achieving an R of 0.737 Dog Breed Classifier (WPI) Aug 2024

•Engineered a dog breed classifier using TensorFlow and pre-trained ResNet50, achieving 85% accuracy in multi-class classification across 120 dog breeds

•Applied image augmentation techniques and addressed class imbalance, improving model robustness and generalization by 20%

•Optimized model performance using early stopping and learning rate scheduling, reducing training time by 30%

•Evaluated the model using precision and recall, achieving a F1-score of 0.88 Skills

Programming and Big Data — Python, Java, SQL, Hadoop, Apache Spark, PySpark Statistical & ML Modeling — Regression Analysis, Time-Series Forecasting (ARIMA, VAR), Market Microstructure Models, PCA Machine Learning Frameworks — TensorFlow, PyTorch, Keras, Scikit-learn, NLTK Data Science Tools — Pandas, NumPy, Matplotlib, Seaborn, SciPy, Plotly, Folium Tools — Power BI, Tableau, Excel, GitHub, dagshub, flask, mlflow, Docker Cloud Technologies — AWS (EC2, S3, Lambda, RDS)

Certificates

MySQL Bootcamp (Udemy) — Completed a MySQL course on Udemy and used the skills to develop a database for an Instagram clone project

Contact this candidate