Quantitative Analyst · AI Researcher
// Germany
Combining financial discipline with AI Powered systematic strategies, code-based research and machine learning models for next-generation investing.
I'm a quantitative analyst with 6+ years of experience in mathematical modeling, financial data interpretation and systematic strategy development. I have a BBA and extensive experience in machine learning. I have written over 80 research reports on equities, macroeconomics and digital assets for Seeking Alpha and my analysis has been syndicated to MSN Money.
My work connects rigorous quantitative analysis and artificial intelligence. I have coded 19 systematic trading strategies and developed algorithmic solutions that have been deployed to multiple institutional clients. Now I'm building QuantAI, a platform that automates institutional-grade equity research with a combination of PyTorch ML models and LLM-powered analysis. The aim is to accelerate transparent, code-backed research to the speed of the institution.
"Overfitting is like making a million dollar titanium cage that's perfectly contoured for a mouse that came to your basement last Tuesday. In the backtest you think you’re a statistical genius until a raccoon walks into the basement. The best business models are not trying to predict every whisker of the past, they are just leaving enough room for tomorrow’s surprises."— Yavuz Akbay
Complex mathematical modeling, factor-based equity research, and systematic strategy development with rigorous backtesting frameworks.
Applying PyTorch and LLM frameworks to financial data — from ML-driven stock selection to automating institutional research pipelines.
End-to-end development of automated trading systems — from strategy conception to live deployment with emphasis on risk-adjusted returns.
80+ published reports covering AI infrastructure, energy, semiconductors, REITs, and behavioral finance — syndicated to MSN Money.
Deep research on data center economics, semiconductor ecosystems, power infrastructure, and AI "picks and shovels" investment themes.
Quantitative analysis of Bitcoin market cycles, holder cohort analysis, on-chain metrics, and intrinsic valuation models for digital assets.
Python simulation of asset price paths using GBM — the mathematical backbone of the Black-Scholes model. Used for option pricing, Monte Carlo risk analysis, and portfolio stress testing. 57 stars, 13 forks.
Python implementation of the Heston model for option pricing under stochastic volatility — captures the volatility smile that Black-Scholes misses. Includes calibration routines and Greeks computation.
Mean-reverting stochastic process for modeling interest rates, commodities, and pairs trading strategies. Includes parameter estimation, simulation, and statistical validation tools.
Portfolio optimization via HRP — uses hierarchical clustering and graph theory to build diversified, robust portfolios without inverting the covariance matrix. A machine learning approach to allocation.
Open to research collaborations, job offers and conversations about quantitative finance, AI and investing.
[email protected]