Machine Learning Data Science

ADITYA SANJAY MALKAR

Jersey City, NJ 551-***-**** *******@*******.*** LinkedIn

PROFESSIONAL SUMMARY

Results-driven Data Science professional with deep experience in machine learning, data engineering, analytics, and deep learning, balancing technical acumen with passion for real-world problem-solving. Proven background in data pipeline design, robust model delivery, data visualization, and collaboration across cross-functional teams. Skilled at building end-to-end solutions to bridge the gap between data insights and impactful decision-making, focusing on innovation and continuous improvement. EDUCATION

Stevens Institute of Technology – Hoboken, NJ, USA Anticipated Graduation: May 2026 Master of Science in Data Science GPA – 3.7

University of Mumbai – Mumbai, Maharashtra, India Graduated: May 2024 Bachelor of Engineering in Computer Engineering CGPA - 8.37 SKILLS

• Programming & Tools: Python, R, SQL, MongoDB, Flask, Django, AWS, Git, GitHub, Google Cloud

• Libraries & Frameworks: NumPy, Pandas, TensorFlow, Scikit-learn, MediaPipe, NLTK, Matplotlib, PyTorch

• Data Engineering and Analytical Skills: Spark, ETL Pipelines, Hypothesis Testing, Regression Analysis, Power BI

• Soft Skills: Excel, Problem-solving, Critical Thinking, Team Collaboration, Time Management, Adaptability, Creativity EXPERIENCE

Prodigy Infotech, (Machine Learning Intern) – Mumbai, Maharashtra, India [Aug 2023 – Oct 2023]

• Collaborated on VisionNet project utilizing image classification algorithm. Improved model accuracy by 15% through hyperparameter tuning and feature engineering.

• Applied Random Forest machine learning algorithms to datasets, increasing prediction accuracy by 12% on a image segmentation task.

TechnoHacks Edutech, (Machine Learning Intern) – Nashik, Maharashtra, India [Jun 2023 – Aug 2023]

• Built an Adaboost based ML model that combined the Random Forest and SVM algorithms which identified and addressed missing data and outliers, resulting in a 20% reduction in model error rates.

• Implemented data preprocessing techniques, Outlier Detection and Removal, SMOTE which reduced the processing time by 30%, enhancing data quality for downstream modeling. RELEVANT COURSEWORK

• Deep Learning

• Big Data Technologies

• Statistical Modeling

• Natural Language Processing

• Data Warehousing & Mining

• Database Management System

CERTIFICATIONS

• Career Essentials in Data Analysis, Microsoft Certificate

• Google Cloud Data Engineering Foundations, LinkedIn Learning Certificate

• AWS Cloud Foundations, AWS Academy Certificate PROJECTS

MultiModal Twitter Sentiment Analysis, MS Data Science Link

• Preprocessed and cleaned 1.6 million tweets, leveraging techniques like tokenization, stopword removal, stemming/lemmatization, and handling of special characters, hashtags, and emojis to improve model efficiency.

• Implemented a deep learning pipeline using Sequential Model architecture with Keras, including Embedding, Conv1D, MaxPooling1D, and LSTM layers, achieving high classification accuracy of above 85% on a dataset of raw tweets. GYM Buddy, BE Computer Engineering Link

• Used MediaPipe to track 15 key body landmarks with 95% accuracy, improving user workout performance tracking by 25%.

• Designed an interface that reduced workout setup time by 40% after implementation of customization features. Human Activity Detection, BE Computer Engineering Link

• Processed 100 hours of video data, improving video quality by 20% through resizing and noise reduction, which enhanced model accuracy by 18% in detecting human activities.

• Utilized OpenCV to extract relevant features from frames and trained a machine learning model, focusing on CNNs for spatial and temporal information.

Contact this candidate