📈 Analyze press releases to predict earnings announcement returns using structured data and natural language processing techniques.

⚡ Streamline option pricing with ML surrogate models, achieving 100-1000x speedup and <1% error for efficient real-time risk management.

📈 Analyze how rumors affect investment decisions using a qualitative reasoning engine for better outcomes and informed choices.

just a little bet (on vn30f1m)

UnifiedVol is a modern C++20 quantitative finance library for volatility surface construction, model calibration, and derivatives pricing.

Quant

Differentiable Programming Algorithms in Modern C++

An Algo that Calibrates Base Correlation for CDO Tranches with as Little as Two Iteration to Machine Precision

End-to-End Python implementation of "FedSight AI" multi-agent system for Federal Funds Target Rate prediction (NeurIPS 2025 Workshop). Simulates FOMC deliberations using LLMs with Chain-of-Draft reasoning and In-Context Learning. Integrates structured macro indicators with unstructured narratives (Beige Book, Dot Plots).

A Python library for evaluating option trading strategies.

Quantamental Portfolio Allocators: Deriving Alpha from Fundamental Metrics with ML

A novel, hybrid AIT-MDL framework for detecting systemic regime shifts (structural breaks) in complex, non-stationary systems. This repository contains the computational narrative and all code to reproduce the findings of our paper on using predictive error as a direct measure of local rule incoherence.

A quantitative framework modeling recursive interactions between technology, capital, and delayed information absorption.

End-to-End Python implementation of CompactPrompt (Choi et al., 2025): a unified pipeline for LLM prompt and data compression. Features modular compression pipeline with dependency-driven phrase pruning, reversible n-gram encoding, K-means quantization, and embedding-based exemplar selection. Achieves 2-4x token reduction while preserving accuracy.

Financial market simulations combining stochastic models (GBM, Heston) with agent-based modeling. Explores price dynamics through different trader behaviors - fundamentalists, chartists, noise traders, contrarians, and institutional players. Built with Python for anyone interested in quantitative finance and computational economics.

GPU-accelerated Monte Carlo simulation of stock prices using Geometric Brownian Motion in CUDA

End-to-End Python implementation of Wu et al.'s (2025) ICAIF'25 paper. It translates unstructured earnings press releases into quantifiable market signals. Implements oLDA topic modeling, Transformer embeddings (BERT/FinBERT/MPNET), GPT-4o interpretability, and rigorous econometric analysis.

Computational Financial Mathematics

Monte Carlo simulation toolkit for equity trading, utilizing GBM and Pareto distributions to model price movements and trading volumes

Advanced numerical methods for option pricing using PDEs with ML surrogate models for real-time risk management. Achieves 100-1500x speedup with <1% error.