Systemic Risk Prediction Based on Savitzky-Golay Smoothing and Temporal Convolutional Networks

Speaker：Lai Yongzeng (Professor, Wilfrid Laurier University , Canada)

Host：Zeng Yan, Professor, Lingnan College

Time and Date：9:00, Jul. 17, 2023

Venue: Wang Daohan Conference Room(101), Lingnan Hall

Language: English + Chinese

Abstract:

This paper discusses the prediction of systemic risk in the Chinese financial market using Savitzky-Golay Smoothing and Temporal Convolutional Networks. Based on the data from January 2007 to December 2021, this paper selects 14 representatives from four levels of the extreme risk of financial institutions, the contagion effect between financial systems, volatility and instability of financial markets, liquidity, and credit risk systemic risk. By constructing a Savitzky-Golay-TCN deep convolutional neural network, the systemic risk indicators of China’s financial market are predicted, and their accuracy and reliability are analyzed. The research found that: (1) SavitzkyGolay-TCN deep convolutional neural network has a strong generalization ability, and the prediction effect on all indices is stable. (2) Compared with the three control models (TCN, CNN, and LSTM), the Savitzky-Golay-TCN deep convolutional neural network has excellent prediction accuracy, and its average prediction accuracy for all indices has increased. (3) Savitzky-GolayTCN deep convolutional neural network can better monitor financial market changes and effectively predict systemic risk.

Profile of the speaker:

He received his PhD in Mathematics from the Claremont Graduate University in January 2000 and his MSc in Mathematics from Zhongshan University in 1988. Prior to joining Laurier, He was a postdoctoral fellow at the Centre for Advanced Studies in Finance and Department of Statistic and Actuarial Science at the University of Waterloo (2000-2002).