About
Driven by an insatiable curiosity for technology, I find myself captivated by its dynamic and transformative power. My passion is particularly ignited by Data Science, which I perceive as a potent tool for deciphering intricate data and unveiling profound insights that can shape our future.
Data Scientist & Web Developer.
Unleashing the power of data, one algorithm at a time.
- Age: 24
- Website: https://github.com/shubhamtamhane
- Email: shubhamtamhane2000@gmail.com
- City: Bloomington, IN, USA
- Visa: F1 OPT
- Degree: Master's in Data Science
- University: University of Rochester
- Available Start Date: Immediately
As a Master's student specializing in Data Science, I am passionately delving deeper into the intricacies of data analysis and interpretation. My academic journey in this field is a natural progression from my previous education in Information Technology, which laid a solid foundation for my understanding of the digital world. I am eager to apply my theoretical knowledge and technical skills to practical scenarios, thereby enhancing my learning experience. My goal is to continually evolve as a data science professional, leveraging my academic background and personal interest in technology. I am excited about the opportunities and challenges that lie ahead in my journey of personal and professional growth.
Skills
I am proficient in a wide array of Data Science disciplines, with a strong ability to manipulate, analyze, and interpret complex data sets. My expertise extends to various data science tools and methodologies, enabling me to transform raw data into actionable insights and strategic solutions
- Programming Languages: Python, R, C, C++, Java, Spark
- Database: SQL, MySQL, PostgreSQL, OracleSQL, NoSQL, MongoDB, Google Firebase
- Data Manipulation and Visualization: Tableau, PowerBI, MS Excel
- No Code Software: JMP, Dataiku, Seeq, Git
- Framework and Libraries: Sklearn, OpenCV, Tensorflow, Keras, Pandas, Numpy, ggplot2, pytorch
- Machine Learning Methods: Linear Regression, Logistic Regression, Decision Trees, Random Forest, Naive Bayes, K-Nearest Neighbors, Support Vector Machines, Artificial Neural Networks, Deep Learning, Gradient Boosting algorithms (GBM, XGBoost, LightGBM), Principal Component Analysis, ARIMA, SARIMA, State Space Models, Holt-Winters Method, Exponential Smoothing.
- Web Technologies: HTML5, CSS3, Django, Flask, Nodejs, , JavaScript, Express, Flutter
Resume
Kindly peruse the following for a comprehensive overview of my educational and professional experience.
Education
Master of Science - Data Science
Aug 2022 - Dec 2023
University of Rochester, Rochester, NY, USA
- GPA: 3.95/4
- Recipient of 40% merit scholarship
- Secured 2nd position in the 2022 UR Biomedical Data Science Hackathon
- Relevant Courses: Time Series, Data mining, Statistics, NLP, Machine Learning, Big Data
Bachelor of Engineering - Information Technology
Aug 2018 - May 2022
Ramrao Adik Institute of Techology, Mumbai, MH, India
- GPA: 3.73/4; CGPA: 8.95/10
- Hackathon winner for creating video conferencing web application. Was invited next year to give guest lecture
- Relevant Courses: Time Series, Data mining, Statistics, NLP, Machine Learning, Big Data
Software Experience
Software Intern
Sept 2022 - June 2023
URMC - Center for Advanced Brain Imaging and Neurophysiology, New York, NY
- Created a distributed ETL pipeline to process over 10,000 DICOM files, reducing ingestion time by 50% by leveraging Python (PySpark) for metadata extraction and storing structured data in MySQL.
- Orchestrated automated data validation workflows, enabling ingestion of new DICOM files by employing Apache Airflow to enforce data integrity checks before storage.
- Containerized the data pipeline, enabling cross-platform execution and reducing deployment time by 80% using Docker
Software Intern
Department of Information Technology, RAIT, India
- Engineered a multi-user video communication application utilizing Express and Node.js.
- Implemented competitive programming practices, resulting in a 10-50% performance optimization in C/C++.
Jun 20-Jul 20
Dec 19-Jan 20
Data Science Experience
Data scientist
Mar 2024 - Present
Indiana University, Bloomington, IN
- Incorporated Microsoft SQL Server in combination with Python for in-depth analysis of healthcare datasets, exceeding 5M records, to derive insights from Electronic Health Record (EHR) data.
- Enhanced data quality by applying feature engineering, outlier detection, and missing value imputation using advanced data preprocessing techniques in Python (Pandas, NumPy).
- Developed a classification model for disease prediction with recall of 85% by implementing XGBoost in scikit-learn.
- Collaborated with researchers to predict survival activity, improving prediction reliability by 30% by implementing deep learning architectures in PyTorch trained on patient’s food intake and activity records.
Data Science Co-op
Jun 2023 - Dec 2023
Regeneron Pharmaceuticals, New York, NY
- Implemented time series forecasting approach to predict customer demand of a complex inventory management problem employing multiple approaches including statistical and deep learning methods.
- Deployed a webapp built using python-dash that leverages MLOps workflow built on cloud-infrastructure to provide real-time up-to date data and forecasting predictions, customer analysis and model maintenance options to end users contributing significantly to cost optimization.
- Led the development of a maintenance analysis system, optimizing the upkeep of MFCs and related systems, which resulted in substantial monthly savings.
- Adopted JIRA for task tracking and Confluence for documentation, adhering to the Agile/Scrum methodology.
Data science intern
Oct 2020 - Jan 2021
Sciffer Analytics Pvt Ltd, India
- Managed the development of image datasets using labelimg tool for information extraction from Google in 3 months empowering a computer vision model to recognize over 30 distinct objects.
- Employed the YOLO v3 model to build a deep learning classifier model, attaining an accuracy rate of 80%.
Campus Leadership Activities
Event Head
Apr 2020 - May 2020
Ramrao Adik Institute of Technology, RAIT-ACM, India
- Organized and mentored Dark Raptor event making it a success by selling more than 200 tickets, accounting for 20% of event’s revenue
Event Organizer
Apr 2019 - May 2019
Ramrao Adik Institute of Technology, ITSA, India
- Collaborated with 3 teammates and contributed to 30% of event’s revenue as the Event organizer by selling more than 60 tickets. Also maintained track of all events in the fest with the use of Microsoft Excel
Portfolio
- All
- Data Science
- Web Development
Emotion Recognition Using Deep Convolutional Neural Networks.
Python, Machine Learning, EDA
A deep convolutional neural network (DCNN) was created and used to identify the mood of the user based on his facial expression. Accuracy of over 83.9% was achieved.
Predicting and Analysing the Viral Fragments of Songs
Python, Machine Learning, EDA
Utilized dynamic time warping to compare extracted MFCC features from songs, and applied a weighted SVM classifier. Achieved 100% recall and 86% accuracy due to presence of data imbalance.
Dynamic QA Generator for Research Papers
Python, Large Language Models, Data Preparation, OpenAI API
Developed a QA model to aid efficient comprehension of research papers by summarizing relevant information in the form of Q&A. Fine-tuned T5 models on OpenAI-modified QASPER dataset with 1.5k+ papers for question generation and answer generation task
Student Performance in Exams
Python, Machine Learning, EDA
EDA of features affecting student's marks and prediction of marks is done achieving 90% accuracy
Mushroom classification
Python, Machine Learning, EDA
Data analysis and usage of Random Forest Classifier on this famous dataset.
Newsletter Signup
MongoDB, Express, Nodejs
It lets me keep you updated with the daily happenings of the world
ToDo List
MongoDB, Express, Nodejs
A Todolist webapp which allows to add,edit and delete tasks on the todolist.
Open to Work
I am available to work for the following roles
Data Scientist
I leverage statistical methods and machine learning to extract insights from complex data sets and drive strategic decisions.
Data Analyst
I interpret data, analyze results using statistical techniques, and provide ongoing reports to help guide business decisions.
Data Engineer
I design, construct, install, test and maintain highly scalable data management systems, ensuring that all data systems meet business requirements and industry practices.
Machine Learning Engineer
I design and build intelligent systems that learn from and make decisions or predictions based on data.
Web Developer
I create and maintain websites, ensuring they're both user-friendly and functional across various platforms.
Software Engineer
I design, develop, and maintain software systems, ensuring they're efficient, reliable, and meet the needs of users.
Contact
I would greatly appreciate the opportunity to connect and engage in a more personal dialogue if you are in the vicinity. It would be a pleasure to meet and discuss our mutual interests further. Feel free to reach out directly at shubhamtamhane2000@gmail.com
Location:
Bloomington, IN
Email:
shubhamtamhane2000@gmail.com
School Email:
stamhane@ur.rochester.edu