Greetings!
My name is Roman Kyrychenko, and I am a Data Scientist with over eight years of experience in data analysis, research, machine learning, and deep learning. I am currently pursuing a PhD at the University of Helsinki, where my research focuses on the dynamics of political polarization and propaganda analysis, particularly in the context of Ukraine.
I have delivered more than 500 hours of lectures on Data Science, Big Data, Deep Learning, and R development. My professional experience spans leading advanced data science and deep learning projects across diverse domains.
Why “Random Forest”?
Random forests are a powerful ensemble learning method that operates by constructing a multitude of decision trees during training. The name “Random Forest” seemed like a fitting — and fun — pun for a data science blog. It reflects my approach: combining rigorous methodology with a touch of creativity.

Expertise and Interests
In this blog, I cover R development, advanced machine learning techniques, sophisticated plotting with ggplot2, web scraping, spatial analysis, and research into polarization and propaganda.
Languages & frameworks: Python (PyTorch, LangChain, pandas, scikit-learn, FastAPI), R (tidyverse, caret, Shiny), SQL, LaTeX.
Specializations: NLP, sentiment analysis, topic modeling, fraud detection, recommender systems, image classification, network analysis, and LLM-powered applications.
Professional Journey
- Senior Data Scientist / Team Lead at SoftTeco — led projects including job–CV matching with LLMs, one-shot learning classifiers, demand forecasting, and fraud detection.
- ML Engineer at Govitall — worked on GPT-2-like language models.
- Data Scientist at VEON/Kyivstar — developed predictive and segmentation models.
- Co-founder of FOG (AI-powered data analysis) and All-Seeing AI (online propaganda detection).
- Lecturer at Ukrainian Catholic University — teaching R for Econometrics and Football Analytics.
Research
My academic research covers the dynamics of aggressive discourse, social polarization, and public opinion. My PhD thesis, “Examining Polarisation Dynamics: The Case of Ukraine,” uses data-driven approaches to understand complex social phenomena. View publications on Google Scholar →
Interested in collaboration or have questions? Connect with me on LinkedIn or find me on GitHub.