Anastasia Galkova

I build data pipelines, reporting tools, and Python services.

B.A. in Computer Science and EconomicsGraduating December 2026

Looking for entry-level roles in data analytics, business intelligence, and data-focused software engineering.

Open selected workSelected work Résumé (PDF) ›

Estimated annual savings: $9,000from a reporting change I implemented at Oscillas Technologies 16% lower error (RMSE)a Ridge regression model vs. repeating last month's rate 3.53× drawdown-risk separationhighest vs. lowest predicted-risk decile in the out-of-time S&P 500 test

Experience

SQL Data Analyst

Internship Oscillas Technologies Aug–Dec 2025 Chicago, IL

$9,000 in estimated annual savings from a reporting change I implemented and explained to stakeholders, including the technical rationale and business case.
Operational data pipelines for manufacturing sensor and ERP data using SQL, PostgreSQL, SQL Server, and materialized views.
More reliable downstream reporting by standardizing calculations across reporting intervals and reconciling sensor-derived production data with ERP records.

C:\Anastasia> reporting_pipeline.exe

[OK] Load operational data
[OK] Standardize intervals
[OK] Reconcile totals
[OK] Prepare reporting data

Selected work

Quantitative research · 2026

Point-in-Time Equity Drawdown Risk

Can a point-in-time model rank 15% drawdown risk over the next 40 trading days?

I built an out-of-time research pipeline using historical index membership, market data, corporate actions, and SEC fundamentals available as of each prediction date.

Result: Drawdown risk remained rankable out of time, including in a separate, nearly non-overlapping universe.

Pythonpandasscikit-learnpoint-in-time data

Open project ›Code on GitHub ›

Out-of-time results

Sample: 91,299 observations
ROC AUC: 0.671
Highest-risk decile: 26.28%
Lowest-risk decile: 7.44%

[PASS] Frozen model transferred to the S&P 400

Forecasting · 2025–2026

Forecasting the Effective Federal Funds Rate

Ridge reduced RMSE by 16% against the repeat-last-month baseline after I rebuilt the pipeline to prevent leakage.

Pythonscikit-learntime series

Open project ›

Text classification · 2026

Craft Forum Discourse Classification

A TF-IDF and logistic-regression model outperformed the transformer approach on a small, thread-separated dataset.

NLPPyTorchexperimental design

Open project ›

Additional work

Testing Versioned Prompt Templates

A PathReview regression test that fails when a protected prompt changes.

Python · pytest · Git

View ›

Leadership · Dec 2024–May 2026

Girls Who Code

President, previously Secretary, Lake Forest College chapter. I organized or led about 20 workshops and campus events and helped grow regular attendance to roughly two to three times its earlier level.

I led technical workshops, including one on internships, and mentored high school students in Python and AI through the Girls Who Code Mentoring Corps.

Education

Expected December 2026

Lake Forest College

Lake Forest, Illinois

B.A. in Computer Science and Economics

GPA 4.00 · Phi Beta Kappa
Dean's List · Presidential Scholarship · Plansoen Family Scholarship

June–August 2026

CodePath

Applications of AI Engineering (AI201)

10-week, instructor-led program

Built a Python retrieval-augmented generation (RAG) service that retrieves relevant passages and cites its sources, then designed and tested a Flask REST API for LLM classification with confidence scores and rate limiting.

Tools

Data

SQL

PostgreSQL SQL Server ETL

Python + backend

Python

Flask REST APIs

Development + testing

Git

pytest

Applied AI + ML

scikit-learn

PyTorch RAG

About

I grew up in Russia, lived in Hong Kong, and now study near Chicago.

Outside class and work, I knit, paint, and travel.

Anastasia standing in front of a palace building in Bangkok

Send me a message

If you're hiring for an entry-level role in data analytics, business intelligence, or data-focused software engineering, I’d be glad to hear from you. I’m also happy to talk about a project.

anastasia.v.galkova@gmail.com

GitHub Résumé