Skip to content
View IndianaBug's full-sized avatar
3 followers · 6 following
  • Solo Dev
  • Lisbon, Portugal
  • 16:02 (UTC -12:00)

Block or report IndianaBug

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
IndianaBug/README.md

Pavlo Vanat

Solo developer focused on data engineering and machine learning for algorithmic system development.

I work primarily on high-throughput data pipelines, time-series processing, and ML-driven decision systems. My background includes backend and server-side engineering, with hands-on experience operating containerized infrastructure.

Tech

  • Python, Rust
  • Data engineering & time-series systems
  • Machine learning for algorithmic strategies
  • Backend & infrastructure (Kubernetes)

Current focus

  • Algorithmic trading bots
  • Real-time market data ingestion and processing
  • Research & experimentation in ML-driven strategies

Collaboration

If you’re interested in training algo bots, I can provide polished, ML-ready datasets inspired by methods from Marcos López de Prado, with extensive feature engineering and labeling pipelines.

Feature sets include trades, l2books, and volatility-derived signals (e.g. impact, intensity, bursts, exhaustion, VPIN-style metrics), applied consistently across multiple data dimensions — not limited to raw trades alone. Pipelines are designed for hyperparameter optimization over execution logic, depth dynamics, and feature interactions. (funding and open interest features coming soon)

Open to collaboration on technically challenging, research-driven projects.

📫 Contact

Popular repositories Loading

  1. fixedbar-failure fixedbar-failure Public

    Crypto market data aggregator for order books, trades, liquidations, and open interest by depth levels. Experimental toy project — unsuitable for production or ML training.

    Python 13 5

  2. distributed-crypto-streaming-attempt distributed-crypto-streaming-attempt Public

    Experimental attempt to aggregate all crypto market streams in one place via a distributed streaming architecture. Abandoned due to excessive production complexity

    Jupyter Notebook 4 1

  3. rl-portfolio-experiment rl-portfolio-experiment Public

    University project exploring reinforcement learning (DQN) for portfolio allocation. Educational experiment, not intended for real trading systems.

    Jupyter Notebook 3

  4. lazy-nvim-stuff lazy-nvim-stuff Public

    A personal Neovim configuration focused on speed, simplicity, and modern development. Includes Python, Rust, and Lua language support, AI autocompletion via Codeium (Windsurf), a transparent backgr…

    Python

  5. mini-fintickstreams mini-fintickstreams Public

    High-performance Rust service for streaming real-time crypto and financial market data — trades, order books (L2), open interest, funding, and liquidations — built for Kubernetes.

    Rust

  6. IndianaBug IndianaBug Public

    Solo developer specializing in data engineering and machine learning for algorithmic systems. Experienced in Python and Rust, backend development, and server-side infrastructure with Docker and Kub…