Joint Workshop on Digital Finance in ASE Bucharest
The Bucharest University of Economic Studies (ASE) is pleased to invite you to participate in the Digital Finance Workshop, scheduled for January 16-17, 2025. The workshop will be held at the Bucharest University of Economic Studies, located at Piața Romană 6, Bucharest.
This workshop, organized through a collaboration between MSCA DIGITAL FINANCE, IDA Institute Digital Assets, AI4EFin, and the Institute for Economic Forecasting of the Romanian Academy, will feature presentations and discussions on cutting-edge topics in Digital Finance, particularly focusing on AI-driven solutions for financial markets, blockchain, digital currencies, and economic forecasting using digital tools.
Location: Bucharest University of Economic Studies, Piata Romana nr. 6, Building Ion Angelescu, Room Virgil Magdearu (ground floor, main entrance).
Link: https://ase.zoom.us/j/84350805723?pwd=qoaiNnbVKQEF8T1jCLDme8BmbGXplw.1
Contact: Prof. dr. Daniel Traian Pele (danpele@ase.ro), Prof. Dr. Wolfgang Karl Härdle (haerdle@hu-berlin.de), Prof. Dr. Adrian Costea (adrian.costea@csie.ase.ro), Alexandra Conda (alexandraconda8@gmail.com), Raul Bag (raulbag1996@gmail.com), Stefan Gaman (gamanstefan18@stud.ase.ro), Theodor Ginavar (ginavarandrei19@stud.ase.ro), David Siang-Li Jheng (david86888@gmail.com), Rahul Tak (rahulramtak@gmail.com)
Agenda:
16 January
*EET Time
17 January
AI in Digital Finance Online Seminar
Title: Low-Rank and Sparse Network Regression
Speaker: Weining Wang (Department of Economics, Econometrics and Finance, University of Groningen)
Date and time: January 17, 2025 (Friday), 11:00 AM (EET) / 10:00 AM (CET)
Link: https://ase.zoom.us/j/84350805723?pwd=qoaiNnbVKQEF8T1jCLDme8BmbGXplw.1
Authors: Áureo de Paula (Department of Economics, University College London) Yingxing Li (Department of Economics, Xiamen University) Weining Wang (Department of Economics, Econometrics and Finance, University of Groningen)
Abstract: We propose to study the interaction effects of social and spatial networks in the presence of a noisy adjacency matrix. First, we provide evidence that existing network datasets exhibit low-rank, sparse, and noisy structures, and we utilize this information to create a de-noised version of the network.
We employ the Least Absolute Shrinkage and Selection Operator (LASSO) in conjunction with nuclear norm penalization to simultaneously regularize the sparse and low-rank components. We introduce two procedures:
1. A two-step estimator, where we first de-noise the adjacency matrix before using it in regression analysis.
2. A one-step supervised Generalized Method of Moments (GMM) estimator to estimate the regression parameter and the adjacency matrix.
Our results show that our estimation method performs favorably compared to GMM, especially when dense errors are present, and networks are endogenous to measurement errors. Simulation exercises indicate that our method outperforms GMM in estimating the regression coefficients by 50-70% in root mean squared error (RMSE) terms when noise is present in the network and maintains a significant advantage of approximately 60-80% with endogenous networks.
Additionally, we apply our method to the Besley and Coate (1995) (BC) dataset and find our methods deliver estimated spillover and multiplier effects that differ significantly from those obtained using BC. Furthermore, we show how our decomposition can be used to provide reliable and more detailed guidance for policy targeting under constraints.