About Me
I’m a Business Analytics Master’s student in New York, focused on applying data, machine learning, and technology to business decision-making. I work as a teaching and research assistant in business analytics and information technology, helping students build quantitative and programming skills and supporting faculty research with data-driven decisions.
My path has been global: from studying analytics and industrial management in South Korea to earning an engineering and business degree at a leading technical university in Russia, and now continuing my journey in the U.S. This mix of experiences helps me approach problems from different perspectives and adapt across industries and cultures.
I work with Python, R, SQL, and Excel on projects in data analysis, risk assessment, and machine learning. Recently, I’ve been researching ML applications in cybersecurity (log-sequence analysis), analyzing cryptocurrency return distributions in Python, and studying yield curve dynamics in R.
Education
Professional Experience
Graduate Assistant in Accounting & Business Analytics | St. John's University
September 2024 - Current- Analyzed cryptocurrency and financial markets dynamics in Python, assessing return distributions (fat tails), trend effects, and volatility; presented weekly reports to a faculty supervisor and discussed further steps for the research.
- Applied descriptive statistics and regression modeling in R to analyze the shape of the yield curve and forecast yield movements, improving out-of-sample predictive accuracy by 10%.
- Developed AI-driven analytics by integrating AI tools such as OpenAI APIs into R workflows, improving data interpretation and supporting more informed decision-making.
- Tutor undergraduate students for the Business Analytics & Information Systems Department in Statistics I & II, helping them understand core concepts and apply Excel for data analysis (formulas, pivot tables, charts).
Data Analytics Intern | Alfa Bank
September 2023 - May 2024- Collaborated with internal bank departments to define data requirements for mortgage and bank loan analytics projects, retrieved datasets using SQL, and validated data in Excel (lookups, pivot tables, data cleaning) to ensure accuracy and integrity.
- Coordinated and documented data-request meetings with internal stakeholders, aligning requirements with systems experts and ensuring data usage complied with regulatory requirements and internal policies.
- Streamlined Jira, Confluence, and Microsoft Office workflows, improving data-quality tracking efficiency by 25% and strengthening agile coordination across cross-functional teams and client communication.
- Developed executive reports and an intern onboarding guide, reducing training time by 30% and improving knowledge transfer.
Projects
E-Commerce Shipment Delay Prediction
Tech stack: Python, Scikit-learn, GridSearchCV, SMOTE
Built and tuned Logistic Regression, Decision Tree, and K-Nearest Neighbors models on a cleaned and engineered shipping dataset to predict late deliveries. Evaluated models with cross-validation and translated findings into recommendations for carrier selection and customer-facing delivery time windows.
Member Subscription Retention Analysis
Tech stack: Python (Pandas, NumPy, Matplotlib, Seaborn), Excel
Analyzed chapter membership data to identify behavior patterns and retention risks. Built a classification model that segments organizations by member volume and retention risk with high accuracy and created dashboards that support targeted outreach and event planning for the Institute of Internal Auditors New York Chapter.
Yield Curve Econometric Modeling
Tech stack: R (time-series, regression, model selection)
Developed an econometric framework in R to study how the shape of the U.S. Treasury yield curve (normal, inverted, humped) changes over time. Used monthly data on yields together with key macroeconomic drivers such as money supply, inflation, and the federal funds rate, estimating multiple models and comparing their ability to explain shifts in the curve across maturities.
Fat-Tail Analysis of Bitcoin & Ethereum Returns
Tech stack: Python (Pandas, NumPy, Matplotlib, Seaborn, SciPy)
Collected and cleaned historical BTC and ETH price data, built time-series plots and log-return distributions, and compared them to the normal distribution using QQ-plots and multiple normality tests (K-S, Jarque–Bera, D’Agostino, Anderson–Darling). Showed strong deviations from normality driven by volatility and fat tails, with implications for risk management and VaR modeling.
Commodity Market Return Analysis
Tech stack: R, Bloomberg Terminal
Analyzed monthly returns of the S&P 500, oil, gold, and a major currency index from 1983–2023 using histograms, time-series plots, descriptive statistics, and correlation matrices. Identified which assets are most volatile, which months exhibit the strongest fat tails, and how return distributions differ across markets, providing insight for portfolio construction and risk management.
Research and Publications
Machine Learning Framework for Cyberattack Risk, Severity, and Timing Prediction
Role: Master’s Thesis (In Progress)
Working Title: Analytics Framework for Cyberattack Risk, Severity, and Timing Prediction Using Survival-Aware Sequence Modeling
Methods: Survival-aware sequence models, deep learning on log sequences, anomaly detection, evaluation of early-warning performance
Developing a machine learning framework that uses application and system log sequences to predict the probability, severity, and timing of cyberattacks. The research focuses on comparing traditional classification approaches with survival-aware sequence models and studying how early in the attack lifecycle reliable warnings can be generated.
Behavioral Model Deployment for Smart City Transportation Projects
Journal: Processes (MDPI), 2023, 11(1), 48
Title: Behavioral Model Deployment for the Transportation Projects within a Smart City Ecosystem: Cases of Germany and South Korea
Authors: Olga Shvetsova, Anastasiya Bialevich, Jihee Kim, Mariia Voronina
The paper analyzes behavioral models for transportation projects in smart city ecosystems, using case studies from Germany and South Korea to evaluate how traveler behavior and infrastructure interact in practice.
Leadership & Volunteering
Data Analytics Volunteer — IIA New York Chapter
Institute of Internal Auditors, New York Chapter
Analyzed membership datasets in Python and Excel to identify retention patterns, segment organizations by size and churn risk, and support chapter leadership with data-driven decision-making.
Built visual dashboards and presentation-ready summaries for board meetings, helping prioritize outreach efforts and design targeted engagement strategies for member organizations.