Machine Learning Data Science

Liubov (Luba) Tovbin

****@******.*** • https://www.linkedin.com/in/lubaakh • https://github.com/LubaTovbin PROFESSIONAL EXPERIENCE

Data Scientist Nov 2021 - Now Groundtruth, Mountain View, CA

● Worked with large-scale location data, performing advanced data manipulations and constructing data processing systems using Python, SQL, dbt, and Amazon Web Services.

● Leveraging SQL, Python, and AWS, successfully developed and deployed numerous iterations of a system that extrapolated and forecasted advertising campaign visits, leading to better customer satisfaction.

● Independently designed and launched a clustering-based system to identify store employees, enhancing the accuracy of visitation metrics.

● Collaborated with other teams, offering expertise in location data analytics to drive project success.

● Managed diverse responsibilities related to data science projects, from literature research and experiment design to technical writing, presentations, cross-team communication, and code reviews. Data Science Intern Jun 2021 - Jul 2021 GroupSolver, San Diego, CA

● Researched state-of-the-art text parsing and semantic analysis for a system that analyzes consumer surveys and creates a comprehensive idea pool for market research. Documented my findings to highlight the new machine learning models' advantages over those currently used, resulting in accuracy improvement from 69 to 76%.

● Set up a machine learning data pipeline to train and evaluate text parsing and sentence embedding models, which improve inference performance by 10%. This allows for better-automated survey analysis and gives customers the most comprehensive market research insights. Mathematics Teacher Aug 2018 - Jul 2019 Russian School of Mathematics, San Mateo, CA

● Taught a broad math curriculum from 2nd grade to precalculus.

● Evaluated students’ performance and adjusted lessons to meet each student’s needs. FPGA Designer Oct 2010 - Jan 2012 BAE Systems, Jerusalem, Israel

● Developed digital signal processing systems using a hardware description language on Altera’s FPGA chip.

● Tested the entire product, digital and RF, using electronics lab equipment such as oscilloscopes, signal and spectrum analyzers, etc.

TECHNICAL SKILLS

Languages: SQL, Python [PySpark, Numpy, MatplotLib, Pandas, Scikit-Learn, Statsmodels, SciPy, DoWhy] Machine Learning: Regression, Classification, Clustering, Time Series Forecasting, ARIMA Statistics: Linear Regression, Logistic Regression, Multivariate Regression, Mixed Effects Models, Resampling, Bootstrapping, Causal Inference, Bayesian Statistics, A/B Testing AWS: S3, Athena, Amazon Step Functions, AmazonSageMaker, Glue, and more Tools: git, Spark, Kedro, dbt, Tableau

Data Mining: ETL, Advanced data manipulation, cleaning and preprocessing; Exploratory Data Analysis, Data Visualization

Natural Language Processing: Word embeddings, Transformers, SpaCy, Huggingface EDUCATION

M.S. in Computer Engineering, specialization in Data Science, San Jose State University, San Jose B.S. in Electronics Engineering, Jerusalem College of Engineering, Jerusalem B.S. in Physics, Hebrew University of Jerusalem, Jerusalem

Contact this candidate