Anton Andreitsev, Developer in Helsinki, Finland
Anton is available for hire
Hire Anton

Anton Andreitsev

Verified Expert  in Engineering

Data Scientist and Machine Learning Developer

Location
Helsinki, Finland
Toptal Member Since
August 8, 2022

Anton is a data scientist, machine learning (ML) engineer, and data enthusiast with four years of working experience in data assimilation (DA) and machine learning. He has supervised a team of junior and senior specialists and taught machine learning for three years at Moscow State University.

Machine LearningData AnalysisDeep LearningNatural Language Processing (NLP)PythonPandasNumPyPyTorchPySparkSQLBashBig DataComputer VisionRecommendation SystemsHadoopLightGBMNamed-entity Recognition (NER)

Portfolio

Alfa-Bank JSC
Python, Pandas, NumPy, PyTorch, PySpark, Hadoop, Apache Hive, CatBoost...
Rubbles
Demand Forecasting, Time Series, CatBoost, XGBoost, LightGBM, Shapely, PySpark
DOC+
Pandas, PyTorch, GPT, Natural Language Processing (NLP)...

Experience

Python - 6 yearsMachine Learning - 4 yearsData Analysis - 4 yearsPandas - 4 yearsNumPy - 4 yearsSQL - 3 yearsPyTorch - 3 yearsDeep Learning - 2 years

Availability

Part-time

Preferred Environment

Linux, PyCharm, JetBrains DataSpell, Jupyter Notebook

The most amazing...

...thing I've developed is eva, a gynecological bot, used by more than 100,000 users all over the world.

Work Experience

Senior Data Scientist

2020 - PRESENT
Alfa-Bank JSC
  • Worked on investment propensity and uplifting models. Increased a response rate from 0.6% to 2% and reduced marketing campaign costs.
  • Decreased a churn rate from the investment app by 16%.
  • Worked on the investment product recommendation models and increased # of active clients by 3%.
  • Built an ML pipeline for optimal workflow for the team. Worked on model deployment, serving, monitoring, and auto-retraining.
Technologies: Python, Pandas, NumPy, PyTorch, PySpark, Hadoop, Apache Hive, CatBoost, LightGBM, XGBoost, Bash, Recommendation Systems, Apache Airflow, Big Data

ML Engineer

2019 - 2020
Rubbles
  • Worked on demand forecasting for restaurants. Created an algorithm that outperformed the existed forecasting approach.
  • Modeled output interpretability for the demand model. Found insights in demand regulation and action points for stakeholders.
  • Worked on forecasting motor oil blend characteristics. Automatized a new blend creation procedure.
Technologies: Demand Forecasting, Time Series, CatBoost, XGBoost, LightGBM, Shapely, PySpark

Junior Data Scientist

2018 - 2019
DOC+
  • Built eva, the gynecological bot, from scratch. It is used by more than 100,000 users worldwide, and over 75% of users' questions have been correctly matched with relevant articles on the first try.
  • Increased inference speed of symptom recognition from ten to one second on a standard patient's chart.
  • Added value to the final text classification model using texts without labels and their clusters.
Technologies: Pandas, PyTorch, Generative Pre-trained Transformers (GPT), GPT, Natural Language Processing (NLP), Scikit-learn, Bash, Docker, Flask, Named-entity Recognition (NER), Chatbots, Topic Modeling

Product Demand Forecasting for Wildberries

https://github.com/andreitsev/wb
A project for forecasting demand for products on wildberries.ru, one of the leading marketplaces in Russia. The project involves the entire data cycle from raw data parsing to building an ARIMA forecasting model and preparing a dashboard for prediction visualizations.
2016 - 2018

Master's Degree in Applied Mathematics and Computer Science

Moscow State University - Moscow, Russia

2012 - 2016

Bachelor's Degree in Economics

Moscow State University - Moscow, Russia

JANUARY 2022 - PRESENT

Go (Golang) for Beginners

Stepik

JULY 2019 - PRESENT

Neural Networks and Computer Vision

Stepik

JULY 2017 - PRESENT

Algorithms: Theory and Practice. Methods

stepik

Other

Machine Learning, Data Analysis, Econometrics, Statistics, Deep Learning, Statistical Modeling, Neural Networks, Natural Language Processing (NLP), Topic Modeling, GPT, Generative Pre-trained Transformers (GPT), Social Network Analysis, Big Data, Algorithms, Computer Vision, JetBrains DataSpell, Recommendation Systems, Demand Forecasting, Time Series, Chatbots, Deployment, Metabase, ARIMA Models

Languages

SQL, Bash, Python, Go

Libraries/APIs

Pandas, NumPy, PyTorch, PySpark, CatBoost, XGBoost, Shapely, Scikit-learn

Frameworks

Hadoop, LightGBM, Flask

Tools

PyCharm, Apache Airflow, Named-entity Recognition (NER), Cron, Git

Paradigms

MapReduce

Platforms

Linux, Jupyter Notebook, Docker, Amazon Web Services (AWS)

Storage

Apache Hive

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring