Data Scientist

Mya J. Bakhova, Ph.D.

linkedin.com/in/myabakhova myabakhova.blogspot.com

***.*******@*****.*** github.com/Mathemilda

SUMMARY OF QUALIFICATIONS AND SKILLS

Languages: Python (Anaconda, Jupyter Notebook, pandas, scikit-learn, numpy, Keras, tensorflow, SpaCy, nltk), R (RStudio, ggplot2, tidyverse, tidymodels, caret, Rmarkdown, Shiny, Leaflet)

Machine Learning, Deep Learning, Statistical modeling: Linear and Logistic Regressions, ANOVA, k-NN, SVM, Bayesian, random forests, PCA, LMI, LDA, clustering, extreme gradient boosting, NLP, cross-validation with hyper-parameter optimization, image recognition, neural networks like CNN, RNN, LSTM and other forecasting algorithms

Data mining: SQL queries with stored procedures (a gold medal on Hackerrank.com), in particular BigQuery; MongoDB

Apache Spark on DataBricks with PySpark, ML Pipelines

Data visualization, presentation skills

OS: Linux, Windows, Mac

Github version control

SELECTED ONLINE PUBLISHED DATA SCIENCE PROJECTS

99.6% of Russian Troll detection by their tweets with my original features and a customized sklearn Transformer to work in sklearn Pipeline, NLP with Python. Here is my summary article with links to my kaggle notebooks (3 parts): https://tinyurl.com/yyk9bcna I published 2 image recognition projects: https://tinyurl.com/3rcs8jwa https://tinyurl.com/yc3mj7h8 Redone PySpark scripts of Machine Learning pipeline, PySpark: https://bit.ly/3pLDPgZ A/B testing, video for methods working in real time: https://bit.ly/3xcDeZe Shiny app for bacterium counts on San Diego coast line: https://tinyurl.com/37aw6ap9 PROFESSIONAL EXPERIENCE

Data Scientist/Analyst Independent Contractor (2016 - Present)

Operations research with ML methods

Numerous Regression/Classification analysis projects

Deep Learning projects and consultations for finance and health treatments

Created automated report documents using Rmarkdown

Text pre-processing, network centrality analysis Lead Technologist Auticon (2021, summer)

A small data science project, covered by NDA

Participation in staff training

NLP Lecturer San Diego State University (2020, Spring semester)

Taught graduate students at Linguistics department Statistics and Machine Learning techniques for NLP. Machine Learning Teaching Assistant SuperDataScience(2017 – 2018)

Consulted students on Machine Learning methods, statistical concepts, visualization, programming syntax, and installation issues. In particular A/B testing was covered.

Answered questions up to 6 hours/day, 32-40 hours per week EDUCATION

PhD. Mathematics, Louisiana State University

M.A. Mathematics, University of Oregon

Passed actuarial exams: Financial Math, Statistics, ANOVA M.S. Mathematics, Statistics, Krasnoyarsk State University CITIZENSHIP

I'm a US citizen.

Mya J. Bakhova, Ph.D.

COMMUNITY INVOLVEMENT

Volunteered at evacuee shelters at Louisiana State University campus after Hurricanes Katrina (2005) and Gustav (2008).

Had been participating in event organization for the University International Student Center.

Organized meetup group “San Diego Women in Data Science”.

Contact this candidate