2 papers
q-fin.CP2026
Rethinking Synthetic Scenario Realism: Compatibility, Not Fidelity, Drives Hedging Performance
Ryuji Hashimoto, Masanori Hirano, Ryota Ozaki +1
Deep hedging is a data-driven approach to learn hedging strategies. It relies on synthetic price paths generator, as real market data is often limited for training. Existing approa…
cs.CE2026
Uncovering Residual Factors in Financial Time Series via PCA and MTP2-constrained Gaussian Graphical Models
Koshi Watanabe, Ryota Ozaki, Kentaro Imajo +1
Financial time series are commonly decomposed into market factors, which capture shared price movements across assets, and residual factors, which reflect asset-specific deviations…