Research Seminar: ''Online Portfolio Analysis For High Frequency Trading Based On Recurrent Neural Networks'' (by Xinwei Cao)

Σας ενημερώνουμε ότι την Τετάρτη, 5 Οκτωβρίου και ώρα 15:00-16:30 θα δοθεί διάλεξη της Dr Xinwei Cao, Professor with School of Business, Jiangnan University, China, με θέμα: " Portfolio Analysis For High Frequency Trading
 Based On Recurrent Neural Networks". Η διάλεξη θα πραγματοποιηθεί διαδικτυακά, στα πλαίσια των Ακαδημαϊκών Ερευνητικών Σεμιναρίων του Τμήματος.

Αποτελέσματα συνεργασίας της Dr Xinwei Cao με τον Αν. Καθηγητή κ. Βασίλη Κατσίκη και τον απόφοιτο του ΠΜΣ μας, ΥΔ κ. Σπύρο Μουρτά έχουν δημοσιευθεί πρόσφατα σε θέματα:

  1. Portfolio Selection:
  • V.N. Katsikis, S. D. Mourtas, P.S. Stanimirovic, S. Li, X. Cao, Time-varying mean-variance portfolio selection problem solving via LVI-PDNN, Computers and Operations Research 138 (2022). DOI: https://doi.org/10.1016/j.cor.2021.105582
  • A.T. Khan, X. Cao, I. Brajevic, P. S. Stanimirovic, V.N. Katsikis, S. Li, Non-linear Activated Beetle Antennae Search: A novel technique for non-convex tax-aware portfolio optimization problem, Expert Systems with Applications, (2022)  DOI: https://doi.org/10.1016/j.eswa.2022.116631.
  • V.N. Katsikis, S. D. Mourtas, Predrag S. Stanimirovic, Shuai Li, Xinwei Cao, Time-Varying Mean-Variance Portfolio Selection under Transaction Costs and Cardinality Constraint Problem via Beetle Antennae Search Algorithm (BAS), Operations Research Forum18(2) (2021).    DOI: https://doi.org/10.1007/s43069-021-00060-5
  • A. H. Khan, X. W. Cao, V.N. Katsikis, P.S. Stanimirovic, I. Brajevic, S. Li, S. Kadry, Y. Nam, Optimal Portfolio Management for Engineering Problems Using Nonconvex Cardinality Constraint: A Computing Perspective, IEEE Access, 1–14 (2020). DOI: https://doi.org/10.1109/ACCESS.2020.2982195
  • A. H. Khan, X. W. Cao, Li Shuai, Hu Bin and V.N. Katsikis, Quantum Beetle Antennae Search: A Novel Technique for The Constrained Portfolio Optimization Problem, Science China-Information Sciences(2020).          DOI: https://doi.org/10.1007/s11432-020-2894-9
  1. Fraud Detection:
  • A.T. Khan, X. Cao, S. Li, V.N. Katsikis, I. Brajevic, P. S. Stanimirovic, Fraud detection in publicly traded U.S firms using Beetle Antennae Search: A machine learning approach, Expert Systems with Applications, (2022). DOI: https://doi.org/10.1016/j.eswa.2021.116148
  1. Neural Networks:
  • B. Liao, C. Hua, X. Cao, V.N. Katsikis, and S. Li, Complex Noise-Resistant Zeroing Neural Network for Computing Complex Time-Dependent Lyapunov Equation. Mathematics (2022). DOI:   https://doi.org/10.3390/math10152817
  1. Portfolio Insurance:
  • V.N. Katsikis, S. D. Mourtas, Predrag S. Stanimirovic, Shuai Li, Xinwei Cao, Time-varying minimum-cost portfolio insurance under transaction costs problem via Beetle Antennae Search Algorithm (BAS), Applied Mathematics and Computation 385 (2020). DOI:    https://doi.org/10.1016/j.amc.2020.125453
  1. Meta-heuristic Optimization:
  • A. H. Khan, X. W. Cao, S. Li, V.N. Katsikis, and L. F. Liao, BAS-ADAM: an ADAM based approach to improve the performance of beetle antennae search optimizer, IEEE/CAA Journal of Automatica Sinica, vol. 7, no. 2, pp. 461–471 (2020). DOI:    https://doi.org/10.1109/JAS.2020.1003048

 

==============================================

 

 

Research Seminar Series in Economic Sciences, 2022-2023

 

 

Speaker: Xinwei Cao, Professor with School of Business, Jiangnan University, China

Webpage: https://www.researchgate.net/scientific-contributions/Xinwei-Cao-2167424021

 

Title: Online Portfolio Analysis For High Frequency Trading
 Based On Recurrent Neural Networks

 

Date & Time: Wednesday, October 5th, 2022, 15:00 - 16:30  

Webex Link: https://uoa.webex.com/uoa/j.php?MTID=m6f2d44769f2375bf2090852c432d9ac6

Url: http://www.econ.uoa.gr/ereynhtika-seminaria-research-seminars.html

 

 

Abstract:  The Markowitz model, a Nobel Prize winning model for portfolio analysis, paves the theoretical foundation in finance for modern investment. However, it remains a challenging problem in the high frequency trading (HFT) era to find a more time efficient solution for portfolio analysis, especially when considering circumstances with the dynamic fluctuation of stock prices and the desire to pursue contradictory objectives for less risk but more return. In this talk, a recurrent neural network model is established to address this challenging problem in runtime. Rigorous theoretical analysis on the convergence and the optimality of portfolio optimization are presented. Numerical experiments are conducted based on real data from Dow Jones Industrial Average (DJIA) components and the results reveal that the proposed solution is superior to DJIA index in terms of higher investment returns and lower risks.

 
©2022 MSc in Quantitative Investing