Skip to content
View MichalS16's full-sized avatar
10 followers · 14 following

Achievements

Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Organizations

@JEM207-Data-Processing-in-Python @JEM224-Version-control-with-Git

Block or report MichalS16

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
MichalS16/README.md

About Me

I am a Master’s candidate in Financial Markets and Data Analysis at IES FSV UK, pursuing a Prg.ai Minor. My focus lies at the intersection of Quantitative Finance, Economic Theory, and Artificial Intelligence. I am passionate about leveraging advanced data analytics to solve complex challenges in financial markets and building intelligent systems that turn economic theory into actionable insights.

⚙️ Technologies & Tools

Python   PyTorch   TensorFlow  Pandas  R   Julia   Jupyter   Mathematica/Wolfram   PostgreSQL/SQL   Docker   Linux/Ubuntu   Git   GitHub Actions  LaTeX   Markdown

💻 Personal Projects

  • Discord Chatbot - An AI-driven Discord bot assistant for our university friends' Discord server, designed to streamline daily tasks. The bot features natural language intent processing to orchestrate multi-step tool calls, providing real-time updates on university canteen menus and available portions, the ability to set homework deadlines and receive notifications for multiple users, get current free game deals and Fortnite drop locations. Additionally, it integrates a vector database to perform semantic similarity searches across university theses, helping students find relevant supervisors and view comprehensive supervision statistics on their thesis counts. The system utilises a robust database for secure authentication and internal game state management.

    • Used technologies - Python, PostgreSQL, Gemini AI - LLM and tool calls, Vector database, Docker, GitHub Actions - CI/CD, Format and test coverage by Pytest

  • DynamicPanelModels.jl - A Julia package for dynamic panel data GMM estimation, built as a university final project to fill a gap in Julia's econometrics ecosystem. It implements the Arellano-Bond Difference GMM, Blundell-Bond System GMM, and Anderson-Hsiao IV estimators, with one-step/two-step estimation, cluster-robust standard errors, and the Windmeijer (2005) finite-sample correction validated against the original papers' published results rather than just internal tests passing. It ships a full diagnostics suite (Sargan/Hansen J-test, Arellano-Bond AR(1)/AR(2) tests, Wald test, Jarque-Bera test, difference-in-Hansen test) and diagnostic plotting, and integrates with the StatsAPI/Tables.jl ecosystem.

    • Used technologies - Julia, StatsAPI/StatsModels/Tables.jl, Distributions.jl, Documenter.jl, GitHub Actions - CI/CD, Format and test coverage by Aqua

  • Senators-trading – A financial analytics platform built with Streamlit that utilises asynchronous scraping to aggregate U.S. Senators' trading data and employs K-Means clustering to identify correlations between political sectors and investment strategies.

Pinned Loading

  1. 42_Prague 42_Prague Public

    C 1