Dr. Ying Chen is a financial statistician and data scientist. She develops statistical modelling and machine learning methods customized for nonstationary, high frequency and large dimensional complex data such as cryptocurrency, limit order book, and renewable energy. She also works on business intelligence, forecasting, text mining and sentiment analysis, and network analysis. Dr. Chen is Associate Professor in Department of Mathematics and Joint Appointee in Risk Management Institute (1 July 2019 to 30 June 2021), National University of Singapore. Dr. Chen is Associate Editor of 5 journals including Statistica Sinica (August 1, 2017 to July 31, 2023), Statistics and Its Interface, Computational Statistics, Digital Finance, and Journal of Operations Research and Decisions. She is ISI Elected Member since March 2016. She is regular member of the Advisory Board of Institute of Statistical Mathematics, Japan from 1 April 2018 to 31 March 2020.
| Name of Speaker | A/P Chen Ying |
| Schedule | Friday 12 March 2021 , 10am |
| Link | https://nus-sg.zoom.us/j/87277632379?pwd=MElkRGxnd2x2QUg4VnFwMUp6WE9iZz09 |
| ID | 872 7763 2379 |
| Password | 247866 |
| Title | Probabilistic Forecasting for Daily Electricity Loads and Quantiles for Curve-to-Curve Regression |
| Abstract | Probabilistic forecasting of electricity load curves is of fundamental importance for effective scheduling and decision making in the increasingly volatile and competitive energy markets. We propose a novel approach to construct probabilistic predictors for curves (PPC), which leads to a natural and new definition of quantiles in the context of curve-to-curve linear regression. There are three types of PPC: a predict set, a predictive band and a predictive quantile, and all of them are defined at a pre-specified nominal probability level. In the simulation study, the PPC achieve promising coverage probabilities under a variety of data generating mechanisms. When applying to one day ahead forecasting for the French daily electricity load curves, PPC outperform several state-of-the-art predictive methods in terms of forecasting accuracy, coverage rate and average length of the predictive bands. For example, PPC achieve up to 2.8-fold of the coverage rate with much smaller average length of the predictive bands. The predictive quantile curves provide insightful information which is highly relevant to hedging risks in electricity supply management. (Joint work with Xiuqin Xu, Yannig Goude and Qiwei Yao. Available at https://arxiv.org/abs/2009.01595) |
