Рабочий

Daniel Rabochyi

Data Scientist | Retail & E-commerce ML | CVM, Forecasting, Personalization

📞 [открыть контакты](см. выше в блоке «контактная информация»)
✉️ [открыть контакты](см. выше в блоке «контактная информация»)
📍 Kyiv, Ukraine

Profile

Data Scientist with hands-on experience in retail and e-commerce analytics, machine
learning, and automation of data/ML processes. Worked on solutions for customer churn
prediction, uplift modeling, promo demand forecasting, personalization, customer
segmentation, and basket analysis.

Experienced in full-cycle ML development: from data collection, feature engineering, and
model training to regular scoring, BI reporting, documentation, and delivering analytical
results to business teams.

Technical Stack

Programming & Data Analysis: Python, SQL, Pandas, NumPy, Scikit-learn
Machine Learning: LightGBM, CatBoost, XGBoost, Optuna
Big Data & Data Engineering: PySpark, Spark, Hadoop/HDFS, Hive, Iceberg, Trino
Databases: PostgreSQL, MS SQL Server
Automation & Analytics Engineering: dbt, Airflow
BI & Tools: Sisense, Git, Jupyter

Project Experience

Churn Prediction 2.0 and Scoring Automation

Retail / E-commerce | CVM | Production Pipeline

Developed a machine learning model for customer churn prediction based on snapshot-based
logic. Prepared behavioral, transactional, promo, and communication features. Trained a
LightGBM model and evaluated performance using ROC-AUC, decile analysis, and lift analysis.

Automated regular customer scoring using dbt, Spark, Iceberg, and Airflow. Built a
production-like workflow for scheduled feature calculation, scoring, logging, and further use
of results by business teams.

Uplift Modeling for Promo Targeting
Incremental Effect | Treatment/Control | XGBoost

Built an uplift model to identify customers who are most likely to generate incremental
response from promo campaigns. Used Treatment/Control logic, Two-Model Approach,
XGBoost, and Optuna for model training and optimization.

Evaluated model performance using Qini Coefficient, decile analysis, and business-oriented
interpretation. Prepared recommendations for promo targeting and customer communication
strategies.

Promo Demand Forecasting

Demand Forecasting | Promo Analytics

Developed a pipeline for forecasting promo sales at the level of products, categories, dates,
and promo mechanics. Used LightGBM, CatBoost, Optuna, ABC segmentation, and business-
oriented error functions.

Prepared Excel-based analytical reports to support promo planning, demand estimation, and
procurement decisions.

Recommendation System and Learning-to-Rank

Personalized Ranking | E-commerce Carousels

Worked on personalized product ranking for e-commerce carousels. Built a user × product ×
carousel × date dataset and aggregated behavioral signals using SQL and Trino.

Trained XGBoost Ranking models and evaluated ranking quality using NDCG@5 and
NDCG@10. The project focused on improving product personalization and recommendation
relevance.

Segmentation, Classification, and Basket Analysis

Customer Analytics | Store Analytics | Product Similarity

Built customer and store segmentations based on purchasing behavior, purchase frequency,
promo sensitivity, and category preferences.

Calculated product similarity using co-occurrence logic, Yule’s Q, and Ward clustering. Used
these approaches to support personalization, targeting, product grouping, and BI analytics.

Data Pipelines, dbt, and Airflow Automation

Analytics Engineering | Scheduled ML Processes
Transferred analytical logic into structured dbt models with staging, intermediate, and marts
layers. Configured Airflow DAGs for regular feature calculation, scoring, logging, and
scheduled production-like execution in Spark, Trino, and Iceberg environments.

Education

Bachelor’s Degree in Computer Engineering

Taras Shevchenko National University of Kyiv
08/2021 – 06/2023

Focus areas: machine learning, model development, model training, hyperparameter tuning,
model evaluation, and performance analysis.

Master’s Degree in Computer Engineering

Taras Shevchenko National University of Kyiv
09/2024 – 05/2025

Thesis topic: Customer Churn Prediction in Retail

Worked on customer churn prediction models, training dataset preparation, feature
engineering, model evaluation, and analysis of customer retention strategies.

Languages

Ukrainian — Fluent
English — B2
Russian — Fluent