arXiv research

Paper proposes a new method for selecting the best hierarchical forecasting approach.

Proposes a neural network for accurate and reconciled hierarchical time series forecasting.

A new hierarchical forecasting method improves overall accuracy.

Study compares local and global models for hierarchical forecasting accuracy.

A new hierarchical forecasting method using machine learning improves forecast accuracy.

Improved prediction of hierarchical time series using structured regularization.

HierarchicalForecast provides a Python framework for coherent hierarchical forecasting.

End-to-end deep model for coherent probabilistic forecasts in hierarchical time series.

A new multi-phase approach improves supply chain forecasting accuracy.

CoRe method improves time series forecasting coherency without strict constraints.

Optimal reconciliation keeps some forecasts unchanged in hierarchical forecasting.

A novel extrapolation method is proposed for longitudinal forecasting. A hierarchical Gaussian process model is used to combine nonlinear population change and individual memory of the past to make prediction. The prediction error is minimized through the hierarchical design. The method is further extended to joint mod…

Extends online linear regression to handle multivariate data.

New methods improve electricity load forecasting using hierarchical transfer learning.

Study improves forecasting of aggregated curves in electricity markets.

Enhances neural forecasting for hierarchically organized time series data.

BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.

Bayesian models forecast COVID-19 hospitalizations at single sites.

We present a comparative study of different probabilistic forecasting techniques on the task of predicting the electrical load of secondary substations and cabinets located in a low voltage distribution grid, as well as their aggregated power profile. The methods are evaluated using standard KPIs for deterministic and …

When forecasting time series with a hierarchical structure, the existing state of the art is to forecast each time series independently, and, in a post-treatment step, to reconcile the time series in a way that respects the hierarchy (Hyndman et al., 2011; Wickramasuriya et al., 2018). We propose a new loss function th…

Graph-EFM models weather uncertainty with graph-based ensembles.

Proposes a new algorithm for efficient probabilistic reconciliation of forecasts.

A new Bayesian model improves forecasting for intermittent demand.

Improved sales forecasting at various levels using ensemble methods.

The paper proposes blending gradient boosted trees and neural networks for hierarchical time series forecasting.

HANET combines LSTM and attention mechanisms for better financial forecasting.

The study improves prediction regions for hierarchical data using a projection step.

Challenge forecasts EV charging station usage accurately.

Unified framework for integrating linear constraints in time series forecasting.

The paper proposes count echo state networks for forecasting graduate student enrollments.

Bayesian consensus improves accuracy of forecasts from miscalibrated sources.

Long-lead forecasting for spatio-temporal systems can often entail complex nonlinear dynamics that are difficult to specify it a priori. Current statistical methodologies for modeling these processes are often highly parameterized and thus, challenging to implement from a computational perspective. One potential parsim…

New algorithm reduces online regression error in RKHS.

Hierarchical forecasting (HF) is needed in many situations in the supply chain (SC) because managers often need different levels of forecasts at different levels of SC to make a decision. Top-Down (TD), Bottom-Up (BU) and Optimal Combination (COM) are common HF models. These approaches are static and often ignore the d…

In this article, we propose a novel ensemble technique with a multi-scheme weighting based on a technique called coopetitive soft gating. This technique combines both, ensemble member competition and cooperation, in order to maximize the overall forecasting accuracy of the ensemble. The proposed algorithm combines the …

A method for fast, accurate cross-temporal forecasts using machine learning.

Develops a method for probabilistic simulation of renewable energy production at grid scale.

Unified R packages for forecast reconciliation of constrained series.

REGAIN learns optimal auxiliary directions for forecast reconciliation.

Accurate and reliable traffic forecasting for complicated transportation networks is of vital importance to modern transportation management. The complicated spatial dependencies of roadway links and the dynamic temporal patterns of traffic states make it particularly challenging. To address these challenges, we propos…

Diffolio uses a diffusion model for multivariate financial forecasting and portfolio construction.

Graph-based weather prediction adapted for local models.

Paper proposes a new method for predicting DER adoption with hierarchical guarantees.

New models improve stock and wind speed forecasting.

Paper proposes efficient methods for forecasting with large datasets.

We study the forecasting of the power consumptions of a population of households and of subpopulations thereof. These subpopulations are built according to location, to exogenous information and/or to profiles we determined from historical households consumption time series. Thus, we aim to forecast the electricity con…

Hybrid model combines LSTM and ETS for mid-term electric load forecasting.

New findings challenge the importance of forecast accuracy in battery storage optimization, highlighting the role of rank correlation instead.