Categories
News Yanfei Kang

Paper accepted in IJF: Exploring the social influence of Kaggle virtual community on the M5 competition

Authors: Xixi Li#, Yun Bai#, Yanfei Kang* Abstract: One of the most significant differences of M5 over previous forecasting competitions is that it was held on Kaggle, an online platform of data scientists and machine learning practitioners. Kaggle provides a gathering place, or virtual community, for web users who are interested in the M5 competition. Users […]

Categories
Feng Li News

The dqr paper is published in the Journal of Business & Economic Statistics

Title: A Note on Distributed Quantile Regression by Pilot Sampling and One-Step Updating Authors:  Rui Pan, Tunan Ren, Baishan Guo, Feng Li, Guodong Li, and Hansheng Wang Abstract: Quantile regression is a method of fundamental importance. How to efficiently conduct quantile regression for a large dataset on a distributed system is of great importance. We show that the […]

Categories
Feng Li News Yanfei Kang

New Paper: Bayesian forecast combination using time-varying features

Authors: Li Li, Yanfei Kang, Feng Li Abstract: In this work, we propose a novel framework for density forecast combination by constructing time-varying weights based on time series features, which is called Feature-based Bayesian Forecasting Model Averaging (FEBAMA). Our framework estimates weights in the forecast combination via Bayesian log predictive scores, in which the optimal […]

Categories
News Yanfei Kang

Paper accepted in IJF: Exploring the representativeness of the M5 competition data

Authors: Evangelos Theodorou#, Shengjie Wang#, Yanfei Kang*, Evangelos Spiliotis, Spyros Makridakis, Vassilios Assimakopoulos Abstract: The main objective of the M5 competition, which focused on forecasting the hierarchical unit sales of Walmart, was to evaluate the accuracy and uncertainty of forecasting methods in the field in order to identify best practices and highlight their practical implications. However, whether […]

Categories
Feng Li News Yanfei Kang

The FFORMPP paper is accepted in the International Journal of Forecasting

The FFORMPP paper is accepted in the International Journal of Forecasting Thiyanga S. Talagala, Feng Li, Yanfei Kang (2021). FFORMPP: Feature-based forecast model performance prediction. International Journal of Forecasting. (in press) [ arXiv | R package ] This paper introduces a novel meta-learning algorithm for time series forecast model performance prediction. We model the forecast error as a function of time series features […]

Categories
Feng Li News Yanfei Kang

Meet our KLLAB members on ISF 2021

Our KLLAB members will be presenting our work at the invited session of the 41st International Symposium on Forecasting virtually. ECR – Visibility Panel Time: Mon. Jun 28, 2021 11:00 AM – 12:00 PM (UTC+8) https://whova.com/portal/webapp/iiofe_202106/Agenda/1753058 Chaired by Shari De Baets In a world ruled by the internet and social media, it is more important than ever […]

Categories
Feng Li News

Feng Li will be presenting at the ISBA 2021 meeting

Dr. Feng Li will be presenting at the 2021 world meeting of the International Society for Bayesian Analysis (ISBA) on session of C28: Bayesian Inference and Forecasting for Business Problems. Time: Friday, July 2, 6:45 am – 8:00 am Whova Link: https://whova.com/embedded/session/isbaw_202106/1572928/ Meeting Program: https://events.stat.uconn.edu/ISBA2021/programs.html The International Society for Bayesian Analysis (ISBA) was founded in 1992to promote the development and application of Bayesian analysis. By sponsoring […]

Categories
Feng Li News

The dlsa paper is accepted in the Journal of Computational and Graphical Statistics

Authors:  Xuening Zhu, Feng Li and Hansheng Wang Abstract:  In this work we develop a distributed least squares approximation (DLSA) method, which is able to solve a large family of regression problems (e.g., linear regression, logistic regression, Cox’s model) on a distributed system. By approximating the local objective function using a local quadratic form, we are able to obtain a […]

Categories
Feng Li News

New Paper: Forecasting reconciliation with a top-down alignment of independent level forecasts

Authors: Matthias Anderer and Feng Li Abstract: Hierarchical forecasting with intermittent time series is a challenge in both research and empirical studies. The overall forecasting performance is heavily affected by the forecasting accuracy of intermittent time series at bottom levels. In this paper, we present a forecasting reconciliation approach that treats the bottom level forecast as latent […]

Categories
News Yanfei Kang

New Paper: Exploring the social influence of Kaggle virtual community on the M5 competition

Authors: Xixi Li, Yun Bai, Yanfei Kang Abstract: One of the most significant differences of M5 over previous forecasting competitions is that it was held on Kaggle, an online community of data scientists and machine learning practitioners. On the Kaggle platform, people can form virtual communities such as online notebooks and discussions to discuss their models, choice […]