DESLab is exploring new Data Science methods to enhance the quality of data analysis for Economics, Business and Science. In our setting, Data Science includes:
• Machine Learning (e.g. deep neural network, parameter tying, ensemble learning, multi-task learning, few-shot learning, etc.)
• Model averaging (e.g. model averaging for liner and non-linear model, model averaging for volatility models, inference based on model averaging, etc.)
• Causal analysis (e.g. treatment effect estimation, causal inference, DID, matching, etc.)
• Financial Econometrics (e.g. time series forecasting, studies about Value-at-Risk, realized volatility, optimal portfolio, etc.)

We devote ourselves to further develop and extend cross-disciplinary activities in data science through collaboration with researchers from any related fields.