BIT · School of CS · '30

Bridging ML research & product engineering

I build machine learning systems, publish research, and design products people love. Student at Beijing Institute of Technology, crafting at the intersection of data, science, and business.

About me

I'm Emelyanov Ilya, a Machine Learning Engineer, researcher, and product builder based in Beijing, China. Currently and studying Computer Science at the Beijing Institute of Technology on a full international scholarship.

My work spans applied ML research and product engineering — from publishing papers and open-source packages to building platforms people actually use. I believe in clean code, reproducible science, and the discipline of shipping.

Beijing, China BIT · CS · 2026–2030 Full Scholarship Published Researcher PyPI Contributor

Work

SmallGBM

v1.4.0 · Paper

Gradient boosting for small tabular data (n < 1000). Outperforms XGBoost by +0.85%, LightGBM by +1.9%, and has the lowest variance among all models on 27 benchmark datasets. Features robust leaf weights (median + adaptive shrinkage) and stochastic split selection. Published on PyPI and Zenodo.

PythonGradient BoostingPyPI Open Sourcescikit-learnResearch
Model AUC Std
SmallGBM 0.9241 ±0.0676
XGBoost 0.9156 ±0.0792
RandomForest 0.9140 ±0.0788
LightGBM 0.9047 ±0.0752
Paper (DOI) Website PyPI Source

SberCarSubscription ML

ROC-AUC 0.706

Binary classification model predicting user conversion on a car subscription platform. Trained on 1.86M sessions using LightGBM with 13 engineered features. Deployed as a FastAPI service with Docker, serving predictions via REST API. End-to-end: EDA, feature engineering, class imbalance handling, hyperparameter tuning, deployment.

LightGBMFastAPIDocker PandasScikit-learnJupyter
View repository

Rubium — Exam Prep Ecosystem

Open Source · Apache 2.0

Open-source educational platform for exam preparation (ЕГЭ/ОГЭ). Built by students, for students — a living product with real users. Frontend: Vue 3, Vite, Pinia, TipTap. Backend: Go (Gin) + Python. Database: Supabase (PostgreSQL). AI-powered hints, custom mock exams, progress analytics, and collaborative notebooks with KaTeX rendering. Lead Developer in a 3-person team.

Vue 3GoPythonSupabase TipTapKaTeXAI IntegrationOpen Source
Source News Community

Publications

SmallGBM: Gradient Boosting with Robust Leaf Regularization for Small-Sample Tabular Data

Emelyanov, I.

Zenodo (Preprint) · August 2026 · DOI: 10.5281/zenodo.21934674

Gradient boosting machines overfit on datasets with fewer than 1000 rows. SmallGBM uses robust leaf weights — median estimation for small leaves and signal-adaptive shrinkage — combined with stochastic split selection (5 random thresholds per feature) to outperform XGBoost and LightGBM on 27 benchmark datasets (15 synthetic + 12 real-world). Achieves state-of-the-art AUC (0.9241) with the lowest variance (±0.0676) among all compared models.

Education

Beijing Institute of Technology

2026 — 2030
School of Computer Science and Technology · Bachelor's
Computer Science and Technology — courses taught in English. Focus: Machine Learning, Distributed Systems, Algorithm Engineering.
BIT International Student Scholarship — full tuition + dormitory

Skillbox · Machine Learning

2024 — 2026
Professional retraining · Data Science & ML Engineering
18-month intensive program: supervised & unsupervised learning, time series, NLP with transformers, MLOps, production-grade model deployment. Final project: real-time fraud detection system with 94% precision.

What drives me

Tech Business & Startups

I'm passionate about building products from the ground up — not just coding features, but thinking through user needs, architecture, and growth. My project Rubium reflects this: a full educational ecosystem designed, architected, and shipped with a friend. I admire the engineer-led, product-obsessed approach. I want to build things that matter.

Science & Research

I'm drawn to the scientific method — rigorous thinking, data-driven decisions, and the elegance of a well-crafted model. My research on SmallGBM formalizes this: robust leaf regularization and stochastic splits for gradient boosting on small data, validated across 27 datasets. Mathematics is the foundation; the best startups emerge from deep research.

Tech Stack

ML & Data

LightGBMXGBoostSmallGBM Scikit-learnPandasNumPy JupyterSMOTEMatplotlibSeaborn

Backend & API

FastAPIFlaskPostgreSQL SupabaseDockerREST API

Languages

PythonSQLHTML/CSSJavaScript

Tools & Ecosystem

GitVS CodePyPIGoogle Colab

Open for Deals

Looking for collaborators & opportunities

I'm open to research collaborations, startup partnerships, and engineering challenges in ML and product development. If you're building something ambitious — reach out.

Contact