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.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “Cross-series”

Bayesian Forecasting of Stock Returns on the JSE using Simultaneous Graphical Dynamic Linear Modelsq-fin.ST

Study forecasts stock returns on JSE using SGDLMs capturing cross-series dependencies.

problem Accurate forecasting of multivariate time series data.

method Simultaneous Graphical Dynamic Linear Models (SGDLMs) with customised DLMs and importance sampling/mean-field variational Bayes.

result SGDLMs accurately forecast stock data on JSE and respond to market changes.

SGDLMs Dynamic Linear Models Stock Forecasting JSE Bayesian

2023-07-07abs ↗pdf ↗

A multi-series framework for demand forecasts in E-commercestat.ML

New framework improves E-commerce sales forecasts.

problem Short sales times series in E-commerce.

method Global model using Tree Boosting Methods.

result Outperforms state-of-the-art models on real dataset.

E-commerce Sales forecasting Tree Boosting Cross-series Volatility

2019-05-31abs ↗pdf ↗

STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Predictioncs.LG

STanHop predicts multivariate time series with memory-enhanced capabilities.

problem Predicting multivariate time series with memory-enhanced capabilities.

method Sparse Tandem Hopfield Network (STanHop) with two external memory modules.

result STanHop outperforms dense Hopfield models in memory retrieval error.

time series prediction Hopfield network memory enhancement sparse learning multivariate

2023-12-28abs ↗pdf ↗

Modeling Volatility and Dependence of European Carbon and Energy Pricesq-fin.ST

Model predicts volatility and dependencies in EUA and energy prices.

problem Analyzing uncertainty and dependencies in European carbon and energy prices.

method Probabilistic multivariate conditional time series model with VECM-Copula-GARCH structure.

result Forecasting performance evaluated in an extensive rolling-window study.

carbon prices energy prices volatility dependence VECM-Copula-GARCH

2022-08-30abs ↗pdf ↗

Local vs. Global Models for Hierarchical Forecastingcs.LG

Study compares local and global models for hierarchical forecasting accuracy.

problem Challenges in hierarchical time series forecasting, especially in accuracy and information utilisation.

method Developed and evaluated local and global forecasting models (GFMs) to exploit cross-series and cross-hierarchies information.

result Global Forecasting Models (GFMs) outperform local models in hierarchical forecasting accuracy and computational efficiency.

Hierarchical Forecasting Local Models Global Forecasting Models Reconciliation Methods Mean Absolute Scaled Error (MASE)

2024-11-10abs ↗pdf ↗

Deep Generative Transformers for Probabilistic Time Series and Spatiotemporal Forecastingcs.LG

Enformer and GEnformer use Transformers with stochastic learning to forecast multivariate and spatiotemporal data with uncertainty.

problem Uncertainty quantification in multivariate time series and spatiotemporal forecasting.

method Synthesizing Transformer's expressive power with stochastic learning to model conditional distributions directly.

result Enformer and GEnformer yield calibrated probabilistic forecasts and outperform state-of-the-art baselines.

Transformer stochastic learning uncertainty quantification time series spatiotemporal forecasting

2026-03-12abs ↗pdf ↗

Multivariate Financial Forecasting using the Chronos Time Series Foundation Modelsq-fin.ST

Chronos models improve financial forecasting by integrating multivariate data.

problem Improving financial forecasting accuracy using multivariate data.

method Evaluation of Chronos-2 on multivariate and univariate financial forecasting models.

result Multivariate forecasts consistently outperform univariate forecasts, especially for interest rates.

financial forecasting chronos multivariate univariate time series

2026-05-08abs ↗pdf ↗

Sales Demand Forecast in E-commerce using a Long Short-Term Memory Neural Network Methodologycs.LG

Generating accurate and reliable sales forecasts is crucial in the E-commerce business. The current state-of-the-art techniques are typically univariate methods, which produce forecasts considering only the historical sales data of a single product. However, in a situation where large quantities of related time series …

2019-01-13abs ↗pdf ↗

Towards Accurate Predictions and Causal 'What-if' Analyses for Planning and Policy-making: A Case Study in Emergency Medical Services Demandcs.LG

DeepPPMNet forecasts EMS demand and performs causal analyses for policy-making.

problem Accurate prediction and causal analysis of EMS demand for effective policy-making.

method DeepPPMNet, a LSTM-based framework, globally forecasts and analyzes causal relationships using Granger causality.

result DeepPPMNet outperforms traditional methods in forecasting EMS demand and policy-making.

DeepPPMNet EMS demand policy-making Granger causality forecasting

2020-04-25abs ↗pdf ↗

LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patternsstat.AP

LSTM-MSNet forecasts time series with multiple seasonal patterns using a unified model.

problem Forecasting time series with multiple seasonal cycles.

method Decomposition-based, unified prediction framework using LSTM.

result LSTM-MSNet outperforms state-of-the-art methods on various datasets.

time series forecasting multi-seasonal patterns LSTM decomposition forecasting competition

2019-09-10abs ↗pdf ↗

SETAR-Tree: A Novel and Accurate Tree Algorithm for Global Time Series Forecastingcs.LG

A novel tree algorithm improves time series forecasting accuracy.

problem Improving accuracy in non-linear time series forecasting.

method Developed a hierarchical TAR model as a regression tree that trains globally across series, introducing a forecasting-specific tree algorithm with cross-series learning.

result Significantly higher accuracy than state-of-the-art tree-based algorithms and benchmarks across four metrics.

time series forecasting tree algorithm SETAR-Tree TAR models regression trees

2022-11-16abs ↗pdf ↗