Peter Gagarinov

Peter Gagarinov

Software Engineering Architect and Consultant

Biography

Peter Gagarinov is a software engineering architect and an open source enthusiast with a focus on machine learning, trading system, applied financial and mathematical modelling, distributed systems and technical computing.

He leads/works as a consultant for a number of closed-source and open-source development projects including Alliedium and Apache Ignite Migration Tool.

Peter has started his career as quantitative engineer at a bank risk analysis department right after graduating from Lomonosov Moscow State University with Master Degree in Applied Mathematics and Computer Science in 2003. Since then Peter has been involved in a number of commercial research and software development projects around financial modeling, market simulation, development and productizing StatArb trading systems and algorithms (primarily for US stock/index, futures, volatility and electricity markets).

Peter had been involved in academic R&D project Ellipsoidal Toolbox for Matlab up until 2016. His thesis, defended in 2014, focuses on ellipsoidal approximations of reachability domains for linear control systems under uncertainty. It was supervised by Alexander B. Kurzhanski from Lomonosov Moscow State University.

Interests
  • Machine Learning
  • Trading Systems
  • Risk Analysis
  • Software Development
  • Technical Computing
  • Distributed Systems
  • Databases
Education
  • Advanced Deep Learning, 2020 - 2021

    Deep Learning School, Phystech School of Applied Mathematics and Informatics

  • Cours intensifs de français, Feb 2017 - May 2017

    Lomonosov Moscow State University, the faculty of Pedagogical Education

  • PhD in Mathematics and Computer Science, 2014

    Lomonosov Moscow State University, the faculty of Computational Mathematics and Cybernetics

  • MSc in Mathematics and Computer Science, 1998 - 2003

    Lomonosov Moscow State University, the faculty of Computational Mathematics and Cybernetics

Languages

English

Proficient/Advanced

French

Intermediate

Russian

Native

Programming Languages Skills

Python

100%

Java

100%

Julia

$\ge$ 90%

Rust

70%, learning

Matlab

100%

C/C++

50%, haven’t used in a while

Skills

Machine Learning
Statistics
Project Management
Deep Learning
PyTorch
Finance
Financial Markets
Trading Systems
Equities
Derivatives
Options
Volatility Trading
Big Data
Data Analysis
Software Development
Financial Risk
Mathematical Modeling
Technical Computing
Distributed Databases
Apache Ignite
Relational Databases
PostgreSQL
Container Orchestration
Kubernetes
Geospatial Tools

Accomplish­ments

Cours intensifs de français
5317a9055
Project Management Fundamentals
ECM-03466/6

Projects

*
Alliedium AIssistant (2020-present)
ML-based automated issue management, defect classification and bug triaging.
Alliedium AIssistant (2020-present)
Apache Ignite Migration Tool (2021-present)
Apache Ignite Migration Tool is an open-source library for applying Apache Ignite database schema changes.
Apache Ignite Migration Tool (2021-present)
Arch Network Isolator (2021-present)
Finetuned host and Docker network isolation for Arch Linux.
Arch Network Isolator (2021-present)
Awesome Linux Configuration Scripts (2020-present)
A curated set of awesome configuration scripts for various Linux-based systems.
Awesome Linux Configuration Scripts (2020-present)
Awesome Software Engineering (2020-present)
A curated list of awesome software engineering resources.
Awesome Software Engineering (2020-present)
PyTorch Hyperlight (2020-present)
The ML micro-framework built on top of PyTorch-Lightning and Ray Tune to push the boundaries of simplicity even further.
PyTorch Hyperlight (2020-present)
PyTorch ML Development Environment (2020-present)
A set of modern ML-oriented conda and pip packages with versions carefully chosen to make sure a seamless and conflict-free integration.
PyTorch ML Development Environment (2020-present)
Telegram Bot for Neural Style Transfer (2020-present)
Neural style transfer bot for Telegram implemented with Ray Serve, Papermill and AIOGram.
Telegram Bot for Neural Style Transfer (2020-present)
ML-based Clustering System for Large Data Sets (2019)
Iterative clustering algorithm operating on large dataset not fitting into RAM, processing took days.
ML-based Clustering System for Large Data Sets (2019)
Ellipsoidal Toolbox for MATLAB (2013-2018)
Ellipsoidal Toolbox for MATLAB is a standalone set of easy-to-use configurable MATLAB routines and classes to perform operations with ellipsoids and hyperplanes of arbitrary dimensions.
Ellipsoidal Toolbox for MATLAB (2013-2018)
MxBerry Core (2014-present)
Core library for boosting a development in Matlab. The library was originally developed as an auxilary library for Ellipsodal Toolbox for Matlab project back in 2014.
MxBerry Core (2014-present)
PgMex (2014-present)
PgMex is a high-performance PostgreSQL client library for Matlab that enables a Matlab-based application to communicate with PostgreSQL database in the Matlab native way by passing data in a form of matrices, multi-dimensional arrays and structures. The library is written in pure C which gives a significant performance boost for both small and data-heavy database requests. Both Windows and Linux platforms are supported.
PgMex (2014-present)
Equity Deep Learning/StatArb Portfolio Management System (2016–2018)
Deep learning-based semi-automatic trading system for US stock market.
Equity Index Volatility and Correlation Trading System (2013–2015)
ML-based semi-automatic market making and position trading system utilizing statistical arbitrage opportunities in volatility index – equity index future spreads on US market.
Risk Analytics Engine (2015–2016)
Broker-side stress-testing and optimization system for both aggregating and scaling multiple traders/strategies operating with options, futures, ETFs and stocks into a single portfolio for a better profitability/risk ratio for a broker.
Algorithmic Trading Development Environment: BEST Studio (2010–present)
Simulation platform for trading finance. It can simulate exchange functionality, exchange behavior, smart order routers, client behavior, market data sources and all interactions between them with a high degree of realism and consistency. A high-frequency exchange simulator uses a set of ML-based models to replicate a realistic behavior of the market. An integrated order-matching engine allows for tested trading strategies be surrounded by a realistic trading environment which can simulate various stress-testing scenarios (including exotic ones) while still keeping things realistic.
Algorithmic Trading Development Environment: BEST Studio (2010–present)
Equity/Index Options StatArb Portfolio Management System (2008-2013)
Semi-automatic trading system built for US options market making and position trading using a relative value implied volatility modeling based on a statistical forecasting of co-movements of implied volatility surfaces.
High Fidelity Exchange Simulator (2007–present)
Exchange Simulator built for major European investment bank program trading desk which models reaction of market participants on user intrusions (activity that is absent in historical data files) by replaying historical orders flow, processing orders submitted by users according to exchange rules and modeling the market response on these user orders using probability-driven empirically justified models. The simulator uses a set of ML-based models to replicate a realistic behavior of the market. Having a wide range of behavioral settings allows to simulate various (including exotic) scenarios while still keeping things realistic due to an integrated order matching logic and fine-tuned ML models.
High Fidelity Exchange Simulator (2007–present)
Tick Data Storage & Analysis project (2007–2009)
Infrastructure built for US proprietary trading firm for storing and analyzing tick data and order entry data in backtesting and real-time modes, providing an environment for defining and operating value-added metrics calculations in real-time and on historical time spans.
Tick Data Storage & Analysis project (2007–2009)
Energy StatArb Portfolio Management System (2004–2007)
Energy StatArb Portfolio Management System. Semi-automatic trading system built for US energy hedge fund for generating trading recommendations on the market of energy/energy resources futures based on methods of Theory of Probability, Mathematical Statistics and Theory of Graphs, Time Series Analysis.
Implementation Shortfall model (2006–2007)
Model built for major European investment bank program trading desk provides an approach towards calculating optimal order execution schedule based on “implementation shortfall” (ISF) minimization.
Implementation Shortfall model (2006–2007)
Market Impact Model (2006–2007)
Model built for major European investment bank program trading desk provides an approach towards making a quantitative estimates of influence of a market participant on market itself.
Market Impact Model (2006–2007)
Tick data comparison tool (2004)
The tool developed for major European investment bank program trading desk provides means for comparing tick data recorded from multiple sources thus allowing estimating a tick data relative quality.
Tick data comparison tool (2004)
Behavioral testing environment for proprietary intraday trading system (2003–2004)
The environment built for Major European investment bank provides means for backtesting of trading strategies incorporated into existing intraday trading system realizing arbitrage opportunities by trading with combinations of equity baskets and equity index futures.

Recent Publications

Quickly discover relevant content by filtering publications.

Contact