This conference provides an excellent venue for academics, researchers, professionals, practitioners to share and discuss research findings, experiences, and practical issues related to financial econometrics.

Click vào ảnh để xem slide

Ho Chi Minh University of  Banking coordinated with Baria-Vung Tau University to organize an annual international conference on econometrics for the year 2022 (ECONVN 2022). This year's conference took place from January 10 to January 12, 2022, at Ho Chi Minh University of Banking 36 Ton That Dam, Nguyen Thai Binh, District 1, Ho Chi Minh in hybrid mode (online and offline meetings). The conference has the theme of “Financial Econometrics: Bayesian Analysis, Quantum Uncertainty, and Related Topics” and is the fifth event since its very successful predecessor ECONVN2018.

The selected papers presented in the Conference are published in the book series STUDIES IN SYSTEMS, DECISION AND CONTROL under the SCOPUS category and considered in the ISI categories.

Following the success of 4 previous econometric conferences- ECONVN2018, ECONVN2019, ECONVN2020, and ECONVN2021 with the topics respectively of “Econometrics for Financial Applications", “Beyond Traditional Probabilistic Methods in Economics”, “Data Science for Financial Econometrics” and "Prediction and Causality in Econometrics and Related Topic"), during 3 days, ECONVN2022 welcomed nearly 2000 participants and 100 research papers were presented (of which 50% are from foreign authors) in the main and parallel sessions by scientists, lecturers from universities and research institutes, from Vietnam and abroad.

In particular, this conference gathered 20 leading experts and scientists over the world in the fields of economics, mathematics, computer science, data science, artificial intelligence, etc. includes: Professor Hung Trung Nguyen, New Mexico State University, USA; Professor Vladik Kreinovich, University of Texas at El Paso, USA; Professor Daniel Stefan Hain, Aalborg University Business School, Denmark; Professor John Harding, New Mexico State University, USA; Professor Katsuhiro Sugita, University of the Ryukyus, Japan; Prof. Mark Edwin Schaffer, Heriot-Watt University, UK; Prof. Polina Khrennikova, University of Leicester, UK; Professor Poom Kumam, King Mongkut's University of Technology Thonburi, Thailand; Professor Thomas Augustin, Ludwig-Maximilians University in Munich, Germany; Professor Tonghui Wang, New Mexico State University, USA; Prof. Vyacheslav Yukalov, Joint Institute for Nuclear Research, Russia; Prof. William Briggs, Weill Medical College of Cornell University, USA; and Professor Woraphon Yamaka, Chiang Mai University, Thailand; Professor Rakesh Gupta, Griffith University, Australia,…

Topics covered and discussed include Bayesian analysis, quantum uncertainty, predictive modeling, causal inference, machine learning, intelligent data analytics, big data techniques and applications for economics, international economics, financial markets, corporate finance, etc. Typically in the following 03 studies:

In the study “What's wrong with the way we teach estimation and inference in econometrics? And what should we do?" by Professor Mark Schaffer from Heriot-Watt University, the authour argues: The widespread use of "level tests null hypothesis” and p-value in empirical studies have led to widespread criticism from many scholars in recent years. Nearly all of the literature and commentary focuses on practice: how these methods and tools have been used and abused, and how they should be applied. Surprisingly, relatively little is concerned about how we teach econometrics and applied statistics in general. Professor Mark Schaffer recommends that it is possible to teach students how to practice frequentlyist statistics reasonably if the core concepts taught from the outset are “coverage” and “coverage”. interval estimation. From there, the author proposes a number of different tools to communicate these concepts.

Or in the study titled “On The Skill of Influential Predictions” by Professor William M. Briggs from Weill Medical College of Cornell University, USA, the paper shows that: The skill of a model is defined as having better predictive power than a default model or a simpler model. These default models almost always exist. Unskilled models should not be used. All predictions are model-based, implicit or formal. Therefore, predictions to be useful must be skillful. Some predictions are influential, that is, they themselves have an effect in whole or in part on the predicted objects we observe. This article deals with commonly used skill measures in evaluating non-influential predictions for use in influential models.

Research with the title "Predicting trends (economic): Why signature method in machine learning" by Professor Vladik Kreinovich from the University of Texas at El Paso, USA and Dr. Le Van Chon from International University, Vietnam summarize: In many real-world situations, we can predict trends - that is, how the system will change any.

 Some pictures taken at the conference: