Skip to content
View winisza's full-sized avatar

Highlights

  • Pro

Block or report winisza

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
winisza/README.md

Adam Winiszewski

Risk analyst at Societe Generale CIB in Warsaw. Working in operational risk while sharpening SQL, Python, and Power BI on the side. Trying to land somewhere between artist and craftsman with data. Mostly wannabe at this stage, but the direction is set.

What's here

Portfolio projects I'm building through 2026:

  1. Operational loss data analysis. Frequency and severity modeling, Monte Carlo simulation, VaR estimation. In progress.
  2. Credit risk scoring. Logistic regression and gradient boosting on public lending data, with SHAP for interpretability. Later in 2026.
  3. Risk reporting dashboard. SQL backend, Python ETL, Streamlit frontend. Q4 2026.

Each repo has a README covering the problem, the approach, the results, and what I'd do differently next time.

For fun

BassLift. Local audio tool that extracts the bass line from a song, transcribes it to notes, and outputs a 4-string bass tab. Optional MIDI export and an isolated bass WAV. v0.1.0 right now, experimental and rough around the edges, more work coming through 2026.

Background

Two years in operational risk at SG CIB. Three years before that in pricing analysis at 3M Healthcare and UPS. Master in Finance and Accounting from Wroclaw University of Economics.

Moving from pricing into operational risk taught me that most "data work" in banks still happens in Excel. The people who actually change anything write SQL and Python. That's the direction now.

Right now I'm focused on

  • SQL past the basics: window functions, CTEs, query performance
  • Pandas as a working tool rather than a CV bullet
  • GARP Risk and AI certification, exam in October 2026
  • PL-300 Microsoft Power BI Data Analyst

Stack

Python (Pandas, scikit-learn, NumPy), SQL, Power BI, Excel. Git, getting better at it.

Contact

LinkedIn · winiszewski.adam@gmail.com

Popular repositories Loading

  1. BassLift BassLift Public

    Local bass tab extractor and source separator.

    HTML

  2. winisza winisza Public