Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

1122 · Jan 202619922001200920172026
12 results for Score-Driven

The paper explores how score-driven models can approximate rough volatility.

problem Modeling rough volatility with long memory structures.
method Extending score-driven models to include infinite-lag structures and heavy-tailed decay.
result Score-driven models converge to fractional Ornstein-Uhlenbeck processes under appropriate scaling.

Paper improves online time series forecasting by combining natural gradient and robust t-distribution.

problem Online time series forecasting challenges in rapidly adapting to evolving data.
method Reframed neural network optimization as a parameter filtering problem, using natural gradient and Student's t likelihood.
result Natural Score-driven Replay (NatSR) achieves stronger forecasting performance than state-of-the-art methods.

Paper proposes BOCPD for real-time order flow and market impact prediction.

problem Persistent order flow patterns in financial markets.
method Bayesian online change-point detection (BOCPD) with score-driven approach.
result Model outperforms existing models in predicting order flow and market impact.

GAS-Norm improves deep learning time series forecasting in non-stationary settings.

problem Deep learning models struggle with non-stationary time series data.
method Combines GAS model for adaptive normalization with deep neural networks.
result Improves deep learning performance in 21 out of 25 settings.

A new model captures irregularly spaced high-frequency prices and their volatility.

problem Modeling high-frequency prices with irregular spacing and market noise.
method Observation-driven model using Skellam distribution with time-varying volatility and smoothing splines.
result The model provides a good fit to IBM stock data and measures daily realized volatility.

The Split-Session Cluster GARCH model captures tail heterogeneity in overnight and intraday returns.

problem Capturing tail behavior and dependence in multivariate asset returns.
method Convolution-tt distributions, session and sector clustering, block-structured correlation matrices.
result Session-specific and sector-level tail parameters improve model fit and out-of-sample performance.

Novel model captures high-dimensional copulas with spectral dynamics and regularization.

problem Modeling time-varying, asymmetric, tail-dependent copulas in high dimensions.
method Score-driven dynamics for eigenvalues, non-linear shrinkage for biases, parsimonious and scalable.
result Model outperforms recent alternatives in capturing co-movements and diversification potential.

Gradient filters track moving parameters under noisy data and misspecification.

problem Tracking multidimensional time-varying parameters under noisy observations and model misspecification.
method Gradient-based filters update parameters using the gradient of a postulated objective function, evaluated at either the predicted or updated parameters.
result Novel sufficient conditions for exponential stability of the filtered parameter path, and finite-sample and asymptotic mean squared error bounds.