Financial Modeling

If you’re tired of classical GANs hallucinating financial time series that look right but behave wrong, you’re not alone. Markets aren’t just stochastic — they’re structured, memory-laced, and irrational in predictable ways. A recent paper, Quantum Generative Modeling for Financial Time Series with Temporal Correlations, dives into whether quantum GANs (QGANs) — once considered an esoteric fantasy — might actually be better suited for this synthetic financial choreography. ...

One of the most sacred assumptions in financial modeling is the existence of a traded risk-free asset. It anchors discounting, defines arbitrage boundaries, and supports the edifice of Black–Scholes. But what happens when you remove this pillar? Can we still price options, hedge risk, or extract information about funding conditions? In a striking extension of the Lindquist–Rachev (LR) framework, Ziyao Wang shows that not only is it possible — it may reveal financial dynamics that conventional models obscure. ...

Markowitz’s mean-variance portfolio theory has long served as a pillar of modern finance, but in its classical form, it assumes a serene world of continuous returns and static market regimes. This serenity, however, shatters when real-world markets swing between boom and bust, triggering sudden and severe asset price shocks. The new paper by Shi and Xu takes a bold step in modeling this turbulence by embedding regime-switching-induced stock price jumps directly into the mean-variance framework. ...

Most generative models for time series—particularly those borrowed from image generation—treat financial prices like any other numerical data: throw in Gaussian noise, then learn to clean it up. But markets aren’t like pixels. Financial time series have unique structures: they evolve multiplicatively, exhibit heteroskedasticity, and follow stochastic dynamics that traditional diffusion models ignore. In this week’s standout paper, “A diffusion-based generative model for financial time series via geometric Brownian motion,” Kim et al. propose a subtle yet profound twist: model the noise using financial theory, specifically geometric Brownian motion (GBM), rather than injecting it naively. ...