• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Multi Agent Based Modelling on Financial Markets

Student: Astashkin Artemiy

Supervisor: Peter Lukianchenko

Faculty: Faculty of Computer Science

Educational Programme: Data Science and Business Analytics (Bachelor)

Final Grade: 8

Year of Graduation: 2024

In order to construct an arti ficial simulating program on several trading platforms and execute the merging of knoweledge transfering between them, anomalies events,also known as fi nancial time series biffurcations,I used agent- based modeling in my thesis, which simulates trading in financial markets. Due to a lack of such research, the earlier simulators were unable to describe those occurrences. The main focus of our research is on currency trading across many marketplaces. I also investigate the impact of an exchange suspending oper- ations and conduct statistical and visually represented hypothesis testing re- garding transmission.Understanding the key features at work involves a robust theoretical approach, given the fast change of the global dynamics of fi nan- cial markets. The usage of ABM in recent decades has made it possible to understand these behaviours. A flexible simulator for identifying the connec- tions between exchanges and their agents cumulative in luence on state of the trading overall are achieved by this approach.Choosed technique is powerful be- cause it can capture the variety of agents, their decision-making procedures, and the emergent phenomena that arise from their interactions. A research project named "Multi Agent Based modelling On Financial Markets" has been carried out in an e ort to maximize agent-based models' potential. The model- ing of linked financial markets is examined in this paper,pointing out that these exchanges is a graph of linked systems with a permanent stream of data, not standalone ones. The primary objective of this research is to comprehend the intricate dynamics of exchange rapid rare events transfer, and the strategy of different traders in these simulations. Based on a series of presumptions, the study investigates the effects of many factors, including the number and diver- sity of traders, the connectivity of markets, and the magnitude of price shocks caused by one exchange closure. This research provides signifi cant new insights into the behavior of numerous markets and suggests a sound methodology for analyzing such intricate systems. It affects traders, market regulators, and - financial organizations, helping them to make better strategic decisions. This work clarifi es the elements in influencing market behavior, which helps to design more resilient and stable nancial institutions.

Full text (added May 20, 2024)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses