I'm Alexey Popodko — a technically-minded professional with a background in physics, hands-on coding experience, and a strong interest in data, research and machine learning, recently began my journey in Data Science Field.

I'm currently working as a medical physicist at a hospital in Moscow, where I’m involved in radiation treatment planning, quality assurance for linear accelerators, and integrating modern research into clinical practice. My work also includes research activities — from publishing articles to exploring new methods — where I use Python for data analysis and automation.

Recently graduated from Yandex Practicum’s Data Science training program, where I developed a variety of data science projects. I'm always open to learning, collaborating, and contributing to meaningful challenges.

With 6+ years of scientific research experience, I’ve contributed to projects involving brain-computer interfaces, EEG signal processing, and applied medical physics / radiotherapy. These works have been published and presented at scientific conferences. I also participate in lectures and technical training at Lomonosov MSU.

• Statistics & Analysis: EDA, Hypothesis Testing, Bootstrap, Time Series Analysis, Clusterization, Data Visualization
• Machine Learning & Modeling: Linear / Logistic Regression, Decision Trees, Support Vector Machines, Ensemble Methods, Gradient Boosting, Hyperparamenter OPtimization, Cross-Validation, Model Calibration, Stacking
• Natural Language Processing
• Computer Vision & Deep Learning: CNN, FCNN, RNN, Transformers
• Experience using code in clinical research: signal and image processing, beam modeling, statistics and EDA for clinical research, QA data processing

• Languages: Python, SQL
• Data Processing: Pandas, NumPy, PySpark, SQLAlchemy
• Visualization: Matplotlib, Seaborn, Histogrammar
• Machine Learning: Scikit-learn, LightGBM, CatBoost, Optuna, HyperOpt
• Statistics & Analysis: SciPy, Geopy, Phik, SHAP
• NLP: BERT, Transformers, NLTK, SpaCy
• DL: PyTorch, TensorFlow, Transformers, Keras, CUDA, Prophet, CLIP, BERT, FAISS
• Clustering: K-means, HAC, HDBSCAN
• Deploy: Streamlit, Docker

Here you'll find a mix of hands-on projects, experiments, and course work — including ML models, EDA notebooks, and tools I’ve built while studying and exploring data science and machine learning techniques.