The goal of this project was to understand the Polymarket microstructure and the effect of different types of wallets on the price. This research utilizes public 2024 US Election data from Polymarket to analyze market microstructure and the efficacy of algorithmic trading strategies within decentralized prediction markets.
Large language models are increasingly deployed as autonomous research agents in quantitative finance: they read briefs, write strategy code, evaluate simulator output, and propose refinements in a loop.
Most systematic trading strategies apply fixed weights regardless of market conditions. A momentum fund stays long whether the market is trending or oscillating. This paper builds and tests a system that routes capital differently depending on which of four market regimes is active at any given time.
Download PDF Abstract This technical report details the architecture and implementation of the BSIC Quant Library, a Python-based infrastructure designed to centralize and optimize financial data retrieval for the BSIC members. The system is designed to facilitate access to financial data from the association’s members by providing a robust pipeline Read more…
Download PDF Abstract This project develops a coherent framework for modelling the implied volatility surface by combining stochastic volatility, local volatility, and smile-consistent interpolation techniques. Starting from market conventions, risk-neutral valuation, and vanilla option pricing, the work introduces the volatility surface as a mapping from strikes and maturities to implied Read more…
Download PDF Abstract This research presents a Time Series Momentum (TSMOM) trading strategy implemented on highly liquid exchange-traded funds (SPY and GLD), enhanced with a novel macro-instrumented regime switching framework for state-dependent de-risking. Our approach addresses the well-documented momentum crash problem—sudden reversals that can wipe out months of accumulated gains Read more…