Point Forecasting

Point forecasting aims to predict a single, most likely future value of a time series, a crucial task across diverse fields. Recent research emphasizes improving the accuracy and reliability of these predictions, particularly by incorporating uncertainty quantification through probabilistic methods like DeepAR and Bayesian approaches with reservoir computing, or by developing novel techniques such as heteroscedastic quantile regression and conformal inference to generate more informative prediction intervals. This focus on robust and reliable point forecasts, often coupled with probabilistic estimations, is driven by the need for more informed decision-making in applications ranging from resource management in telecommunications to financial market prediction and climate modeling.

Papers

November 20, 2024

Conformal Prediction for Hierarchical Data
Guillaume Principato, Yvenn Amara-Ouali, Yannig Goude, Bachir Hamrouche, Jean-Michel Poggi, Gilles Stoltz
Conformal Prediction Hierarchical Datasets Split Conformal Prediction Point Forecasting Forecast Reconciliation

July 19, 2024

On the use of Probabilistic Forecasting for Network Analysis in Open RAN
Vaishnavi Kasuluru, Luis Blanco, Engin Zeydan
Greater Public Use Probabilistic Forecast Network Analysis Radio Access Network RAN Architecture Point Forecasting

June 21, 2024

Enhancing reliability in prediction intervals using point forecasters: Heteroscedastic Quantile Regression and Width-Adaptive Conformal Inference
Carlos Sebastián, Carlos E. González-Guillén, Jesús Juan
Prediction Interval Conformal Inference Wind Power Forecasting Heteroscedastic Regression Electricity Price Forecasting Point Forecasting

June 20, 2024

Fusion of Movement and Naive Predictions for Point Forecasting in Univariate Random Walks
Cheng Zhang
Hybrid Fusion Motion Prediction Random Walk Biased Prediction Movement Related Information Point Forecasting

October 11, 2023

ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
Jiawen Zhang, Xumeng Wen, Zhenwei Zhang, Shun Zheng, Jia Li, Jiang Bian
Time Series Forecasting Exceptional Point Prediction Horizon Forecast Distribution Point Forecasting

August 24, 2023

Probabilistic load forecasting with Reservoir Computing
Michele Guerra, Simone Scardapane, Filippo Maria Bianchi
Uncertainty Quantification Reservoir Computing Probabilistic Load Point Forecasting

August 17, 2023

Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces
Miguel Liu-Schiaffini, Clare E. Singer, Nikola Kovachki, Tapio Schneider, Kamyar Azizzadenesheli, Anima Anandkumar
Non Stationary Function Space Tipping Point Point Forecasting Climate Tipping Point

September 17, 2022

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network
Takuya Kanazawa, Chetan Gupta
Uncertainty Quantification Single Neural Network Predictive Distribution Deterministic Neural Network Uncertainty Sampling Uncertainty Quantification Method Point Forecasting

June 20, 2022

Exceedance Probability Forecasting via Regression for Significant Wave Height Prediction
Vitor Cerqueira, Luis Torgo
Novel Regression Probabilistic Forecast Extreme Weather Point Forecasting Significant Wave Height

Point Forecasting

Papers

Conformal Prediction for Hierarchical Data

On the use of Probabilistic Forecasting for Network Analysis in Open RAN

Enhancing reliability in prediction intervals using point forecasters: Heteroscedastic Quantile Regression and Width-Adaptive Conformal Inference

Fusion of Movement and Naive Predictions for Point Forecasting in Univariate Random Walks

ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons

Probabilistic load forecasting with Reservoir Computing

Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network

Exceedance Probability Forecasting via Regression for Significant Wave Height Prediction