Python

Advanced cloud-based AI-driven SaaS platform for US real estate market (2022-present)

An advanced cloud-based SaaS platform, currently serving the US real estate market with a focus on geo-analytics and forecasting. It integrates state-of-the-art Generative AI and Machine Learning technologies, enhancing both functionality and accuracy. The platform operates natively with Amazon Web Services (AWS) and Kubernetes, supporting multi-tenancy and ensuring robust security. Its key features include auto-scalability and high availability, providing real estate professionals with reliable, data-driven insights and predictions.

Alliedium AIssistant (2020-2022)

ML-based automated issue management, defect classification and bug triaging.

Awesome Software Engineering (2020-present)

A curated list of awesome software engineering resources.

Scalable machine learning with Apache Ignite, Python and Julia: from prototype to production

Building a distributed and scalable ML-enabled backend on top of Apache Ignite, Ray Serve, Scikit-learn and PyTorch.

An open-source tool for Apache Ignite network isolation in local development environments

Local development with Apache Ignite made simpler on Arch Linux.

Scalable machine learning with Apache Ignite, Python, and Julia: from prototype to production

Peter Gagarinov shares his experience with integrating Apache Ignite with external machine frameworks.

Using Apache Ignite to boost the development of Jira Cloud apps

Peter shares his Apache Ignite experience. He will show how one can minimize the number of blocks in a complex, scalable backend for an ML-based, automated issue-management system (Alliedium), as you stay within the Java ecosystem and the microservice paradigm.

ML-based Clustering System for Large Data Sets (2019)

Iterative clustering algorithm operating on large dataset not fitting into RAM, processing took days.

Equity Deep Learning/StatArb Portfolio Management System (2016–2018)

Deep learning-based semi-automatic trading system for US stock market. The system automatically extracts a sensible information (in form of features for a deep learning model) from both publicly-available and subscription-based sources of daily and high-frequency market data. After a second stage of dimensionality reduction and features re-combination (via back-testing & cross-validation) the most relevant features are then used to train a complex non-linear model on GPU. The portfolio optimization-driven trading strategy uses probabilistic forecasts made by the model and current positions on the market to generate specific instructions for the traders.

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.