My talks
2023:
2022:
- NL-Augmenter: crowd-sourcing transformations (talk in Russian)
- Data Visualization in Data Science | DataHour | Analytics Vidhya
- История разработки медицинского чат-бота (talk in Russian)
- Уроки извлеченные из 10 лет в IT (ERP и DS) (talk in Russian)
- Video Super-Resolution: Approaches to modelling and evaluation.
2021:
- Из бизнеса в Data Science, из DS в DL. Андрей Лукьяненко о своих победах
- Data Visualization in Data Science (Russian version).
- Data Visualization in Data Science.
- Practical aspects of working with NER task (talk in the Russian language).
- Writing reusable training pipelines for deep learning. ML REPA.
- A talk in the Russian language about using Hydra framework for configuration in Python projects.
- Podcast talk about Kaggle, modern ML technologies, frameworks, hardware, and many other things
- Building your Data Science Career: how to become a data scientist
2020:
- Andrey Lukyanenko - Handwritten digit recognition w/ a twist & topic modelling over time
- Pair Programming: Deep Learning Model For Drug Classification With Andrey Lukyanenko
- DataFest 2020 talk: My Kaggle Story
- Overview of approaches to "Mechanisms of Action (MoA) Prediction" competition on Kaggle (3 weeks before the end of the competition)
- Metro Analysis and Visualization
- Writing reusable pipelines in Deep Learning | Mindhack! Summit
- December Lightning Talks. Training pipeline with Pytorch Lightning and Hydra
2019:
- ML Training talks about gold winning solution in Kaggle Predicting Molecular Properties Competition
- An overview of 2019 year in Kaggle, Talk in Russian at ODS.AI event
- Data Halloween: predicting chaotic actions of clients. Talk in Russian at ODS.AI event
- Storytelling with data visualization: case of kaggle kernels. Talk in Russian at Data Fest 2019
My interviews
- Data Science, Kaggle Master, ChatBots and Fraud Detection with Andrey Lukyanenko
- Данные люди: Путь грандмастера — как всё успеть.
- Из бизнеса в Data Science, из DS в DL. Андрей Лукьяненко и своих победах
- Interview with Kaggle Kernels Grandmaster #1: Artgor | Andrew Lukyanenko. Chai Time Data Science | player.fm link
- Kaggle: People, We’ve Gamified Progress
- Kaggle Grandmaster Series – Exclusive Interview with Andrey Lukyanenko (Notebooks and Discussions Grandmaster)
Corporate blogposts
ML competitions
Kaggle ranks
Oct 10, 2019 - Discussion Grandmaster
Aug 29, 2019 - Competition Master
May 08, 2019 - 1st place in Notebook ranking
Feb 21, 2019 - Notebook Grandmaster
Notable competitions
Aug 29, 2019 - 8/2737. Gold medal in Predicting Molecular Properties
Aug 30, 2018 - 64/7176. Silver medal in Home Credit Default Risk
Aug 21, 2018 - 108/4464. Silver medal in Santander Value Prediction Challenge
Oct 20, 2018 - 100/3219. Silver medal in TGS Salt Identification Challenge
Mar 14, 2019 - 120/2410. Silver medal in Microsoft Malware Prediction
Aug 28, 2019 - 87/921. Bronze medal in Generative Dog Images
May 09, 2019 - 23/58 Anti-spoofing challenge
Mar 30, 2018 - 25/92 Geohack competition
Apr 24, 2018 - 3/67 Shop check categorization
Notable kaggle notebooks
EDA and models
1000+ upvotes, 100k+ views. A notebook for IEEE-CIS Fraud Detection competition. EDA, feature engineering, plots with altair, modelling with LGBM.
EDA, feature engineering and everything
900+ upvotes, 110k+ views. A notebook for Two Sigma: Using News to Predict Stock Movements competition. Text and tabular data EDA, analysis of stock market, plots with plotly, modelling with LGBM.
Segmentation in PyTorch using convenient tools
600+ upvotes, 60k+ views. A notebook for Understanding Clouds from Satellite Images competition. EDA, augmentations with albumentations, image segmentation using Catalyst.
Exploration of data step by step
600+ upvotes, 30k+ views. A notebook for PetFinder.my Adoption Prediction competition. A very detailed EDA of tabular and text data, complex plots with matplotlib and seaborn, modelling with LGBM.
How to not overfit?
500+ upvotes, 30k+ views. A notebook for Don't Overfit! II competition. Model interpretation, comparison of many models, comparison of feature selection methods, approaches to feature engineering on anonymized data.
EDA, Feature Engineering and model interpretation
400+ upvotes, 40k+ views. A notebook for TMDB Box Office Prediction playground competition. A very detailes EDA for various types of data, advanced approaches to feature engineering, model interpretation.
EDA, feature engineering and xgb + lgb
100+ upvotes, 8k+ views. A notebook for DonorsChoose.org Application Screening competition. This notebook won a second place in popularity ranking and got me a prize - Pixelbook.
Notable courses completed
Mlcourse.ai
Finished at 5th place. This was a useful course with useful theoretical materials and practical exercises.
Deep Learning Nanodegree with Pytorch on Udacity.
You can read about my experience of going through this course here.
Other activities and achievements
Moscow DataFest 6 (2019) - organized "EDA & Visualization" track.
Open Data Science Awards 2019 Got awards for one on best talks in ML Trainings and for progress in competitions.
Moscow DataFest 2020 - one of organizers of "ML trainings" track.
Open Data Science Awards 2020 Gor awards for one of best talks in Business section and for mentoring.
Completed Hacktoberfest in 2018 and 2020.
Wrote for a week in dsunderhood
I'm one of the main contributors of an open-source project for a topic modelling on news articles