Data Science, Data Analytics, Machine Learning

Atmika Sarukkai

ad027j@r.postjobfree.com, 408-***-****, Location: Cupertino, CA

www.linkedin.com/in/atmika-sarukkai

https://github.com/atmika-sarukkai/data-analytics

EDUCATION

Master of Information and Data Science, University of California, Berkeley Dec 2024 BA, Data Science (Honors), University of California, Berkeley May 2023 Relevant Coursework: Structure and Interpretation of Computer Programs, Data Structures, Linear Algebra and Differential Equations, Principles and Techniques of Data Science, Probability for Data Science, Discrete Mathematics and Probability Theory, Introduction to Machine Learning and Data Analytics, Introduction to Artificial Intelligence, Data Mining and Analytics, Natural Language Processing

EXPERIENCE

Data Science Honors Thesis August 2022 - May 2023

■ Calculated statistics for variance and directionality for comparison of trends in intensity of Twitter negative user sentiment and prevalence of various kinds of crime in San Francisco over time

■ Performed word-vectorization and dimensionality reduction in Python on Tweets for exploring associations between crime and fear sentiment

Data Analytics Technician, Western Digital June 2021 - October 2022

■ Created machine learning models (logistic regression) and data visualizations in Python to improve manufacturing cycle time

■ Worked on feature-based models (including logistic regression, random forest, gradient boosting) for predicting daily number of products manufactured every quarter

■ Created an iterative XGBoost model of lead time ratio (LTR) for automatic robotic vehicles (ARVs) to select optimal ARVs for dispatch

Data Engineering Intern, 3Analytics May 2022 - August 2022

■ Created pipeline for data preprocessing and data cleaning of demographic and health history data in Python for data science team

■ Conducted literature reviews on text-based modeling (NLP, NER) for predicting adverse reactions to drugs and vaccines using text/social media data

Data Science Research Assistant, ReThink Media Jan 2022 - May 2022

■ Developed a machine learning model (random forest) in Python to classify topics and speakers of news articles concerning nuclear weapons/nuclear spending

■ Performed feature extraction using NLP techniques/text analysis

■ Composed a blog post on the results of the news/opinion classifier, summarized team results with visualizations Data Science Discovery Program, UC Berkeley Aug 2021 - Dec 2021

■ Created data visualizations in Python to analyze the relationship between academic probation and academic performance among UC Berkeley undergraduate students

■ Identified significant predictors of placement on academic probation, to identify areas for increased intervention SKILLS

■ Python (Pandas, Matplotlib, SciPy, scikit-learn), SQL, Java, Scheme

■ Data Cleaning, Manipulation, Visualization, EDA

■ Machine Learning/Modeling

■ Text analysis, NLP

■ Spanish (conversational)

AWARDS/HONORS

Data Science Honors Program 2023

Semi-finalist, Siemens Competition 2016, “A Mysterious Population of Stars With Weak CN Absorption in the Disk of M31”

Contact this candidate