Keynote Speakers

Prof. Xianhua Wu

Shanghai Maritime University, China

Executive Director of Shanghai Society of Quantitative Economics

Research area：Big data and management quantitative analysis, disaster risk and emergency management, shipping industry economics

Title：Evaluation of the economic impact of Japan’s Fukushima nuclear wastewater discharge on neighboring countries based on the GTAP model

Abstract: On April 13, 2021, the Japanese government intends to discharge more than 1.2 million tons of nuclear waste water from the Fukushima nuclear power plant into the Pacific Ocean, arousing great attention from governments and people around the world. This article uses the Global Trade Analysis Project (GTAP) used by multiple countries and departments to consider different impact scenarios of nuclear wastewater discharge, and evaluates the impact of the discharge on the macro economy, industry and trade of the relevant country or region. The results of the study are: (1) The negative effects of nuclear wastewater discharge will reduce the GDP of relevant countries or regions, the social welfare loss can be as high as 347.66 billion US dollars, and this impact will increase as the scope of nuclear wastewater proliferation expands；(2) The discharge of nuclear waste water will increase the trade imbalance between some regions and lead to a decrease in the total output value of most countries or regions. This article assesses the economic losses caused by the discharge of nuclear waste water to neighboring countries or regions,  revealing the negative consequences of nuclear waste water discharged into the sea.

Prof. Guoliang Fan

Shanghai Maritime University，China

Council Member of China Business Statistics Association

Research area：Big data statistical analysis, non-parametric and semi-parametric statistical analysis, economic statistics, econometrics, industrial economy

Title：Nonlinear Interaction Detection Through Model-Based Sufficient Dimension Reduction

Abstract: In this talk, we are concerned with nonlinear interaction detection through partial dimension reduction with missing response data. The covariates are grouped through linear combinations in a general class of semi-parametric models to detect their joint interaction effects. The joint interaction effects are estimated by a profile least squares approach with the help of the inverse probability weighted technique. The asymptotic properties of the resulting estimate for the central partial mean subspace are provided. In addition, a Wald type test is proposed to evaluate whether there exists interactions between individual covariate and another group of covariates.  A BIC-type criterion is applied to determine the structural dimension of the central partial mean suspace and its consistency is also established. Simulations are conducted to examine the finite sample performances of our proposed method and a real data set is analyzed for illustration.

Prof. Jianchao Hou

Shanghai University of Electric Power，China

Deputy Dean of School of Economics and Management

Research area：Energy Economy and Management, Carbon Emissions, Power System Optimal Dispatch, Energy Transformation

Title: Mining technology and method of energy big data

Abstract: The big data mining technology and methods for energy and electric power, mainly addresses the big data source, the big data mining methods and the practical application cases of energy and electric power field.

Prof.Defu Zhang 

Xiamen University，China

Research Area: big data, computational intelligence, knowledge graph, deep learning

Title: Machine learning for Stock forecasting

Abstract: This talk mainly introduces different models for stock forecasting, one model combines features selected by multiple feature selection techniques to generate an optimal feature subset and then use a deep generative model to predict future stock movements. Another model is for a turning point prediction method of stock price based on RVFL-GMDH and chaotic time series analysis. The turning indicator of time series is computed firstly; then, by applying the RVFL-GMDH model for the turning point prediction of the stock price. Computation results are reported.

to be added...