Data Scientist

Julia Fliorko

SQL Python Tableau ML
Julia Fliorko headshot

About Me

Education

  • Bachelor’s in Software Engineering
  • Master’s in Data Science (in progress)

Professional Background

  • Data Scientist with a background in Business Analysis, experienced in translating ambiguous requirements into well-defined analytical questions and actionable insights.
  • Strong at bridging stakeholders and data — turning business needs into clean datasets, measurable metrics, and interpretable models.
  • Specialized in working with messy, real-world data: sourcing from APIs, cleaning and merging multiple datasets, and documenting assumptions and limitations.
  • Build end-to-end analytical workflows in Python, from raw data to machine learning models and decision-ready outputs.
  • Recent projects focus on research-oriented datasets in environmental and food-access domains, where data quality and methodology matter more than visuals.

Certifications

  • Career Foundry: Data Analysis

Data analysis is an art — and I’m just the tool that helps reveal the picture hidden beneath the numbers.

Tools & Skills

Programming & Data Manipulation
Python (pandas, numpy, scipy)
  • Data cleaning, transformation, merging large datasets
  • Feature engineering, vectorized operations, performance-aware workflows
SQL (PostgreSQL / SQLite)
  • Joins, subqueries, CTEs, aggregations
  • Data validation, exploratory querying, schema understanding
Data Collection & Integration
  • APIs (REST)
  • Data ingestion, pagination handling, authentication
  • JSON normalization, schema alignment across sources
  • Web data handling (structured extraction)
  • Dealing with inconsistent formats and missing fields
Data Cleaning & Preparation
  • Handling missing data (imputation, exclusion with justification)
  • Deduplication and record linkage
  • Data type standardization and normalization
  • Outlier detection and treatment
  • Data quality checks and validation rules
  • Documentation of assumptions and limitations
Machine Learning
Supervised
  • Classification & Regression
  • Logistic Regression, Decision Trees, Random Forest, K-Nearest Neighbors
  • Model evaluation: precision, recall, F1-score, ROC-AUC
  • Confusion matrix analysis
  • Feature scaling: StandardScaler, MinMaxScaler
  • Hyperparameter tuning: GridSearchCV, RandomizedSearchCV
  • Train / validation / test design (time-aware splits when applicable)
Unsupervised
  • Clustering: K-Means, Hierarchical clustering
  • Dimensionality reduction: PCA
  • Cluster validation and interpretation
Neural Networks (Applied)
  • ANN (feedforward)
  • CNN (spatial data only)
  • RNN / LSTM (sequential data only)
  • TensorFlow / Keras or PyTorch
Time Series & Temporal Analysis
  • Time-based feature engineering (lags, rolling windows)
  • Trend and seasonality analysis
  • Baseline forecasting methods
  • Time-aware validation strategies
Data Visualization & Communication
  • Tableau: interactive dashboards, KPI reporting, geo/time visuals
  • Python visualization: matplotlib, seaborn
  • Translating results into non-technical insights
Geospatial & Structured Data
  • Geographic identifiers (ZIP, census tract, region)
  • Spatial joins and aggregation
  • Distance-based metrics and density calculations
Workflow & Tooling
  • Git / GitHub (version control)
  • Reproducible project structure
  • Jupyter Notebooks / Python scripts
  • Modular, readable code practices
  • Dataset versioning (raw / interim / final)

Portfolio

Filter by Tools

Filter by Skills

Contact

Download Portfolio (PDF)
Download Portfolio (PDF)
LinkedIn Tableau GitHub
jfliorko@gmail.com