H2020Индивидуална стипендия2018–2020

InvestorCliques · Investor Cliques in Stock Markets

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2018-05-01 → 2020-05-15
Финансиране от ЕС: 191 326 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Поведението на инвеститорите и формирането на групи от тях се анализират чрез теорията за сложните мрежи, за да се проследи как разпространението на информацията влияе върху цените на акциите. Това помага на регулаторите да следят пазарите и да планират политики срещу финансови кризи.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Investor Cliques in Stock Markets

Complex networks theory during the last two decades has gained novel results and profound insights into many complex systems in engineering, social and biological and also financial fields. This project applied cross-disciplinary complex network approaches to investigate investor behaviors and explain their impact on asset price dynamics. Moreover, information diffusion in financial markets is a fundamental question, which was addressed by this research. This research is not only academically but also practically relevant as financial supervisory bodies and regulators can benefit from the study to monitor investors in stock markets. Sometimes, investors’ behavior can be related to a (local) information leakage. Additionally, practitioners can benefit from understanding better the origins of crises and booms, derived from the actual observations of the financial agents (investors). Our research allows regulators to plan effective policies to contrast and overcome financial crises in stock markets. The main objectives of every Work Package are given in the following: 1. Network estimation and visualization methods for investor networks 2. Clustering algorithm to detect communities of the investor networks 3. Identify the evolution of investor cliques and track the change in structure of networks 4. Analyze association between network evolution and market movement 5. Develop parallel computing solutions for the existing network models and clustering algorithms using distributed computing platform and big data technology

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

Complex networks theory during the last two decades has gained novel results and profound insights into many complex systems in engineering, social and biological and also financial fields. This proposed data-driven research programme will apply cross-disciplinary complex network approaches to identify investor cliques in stock markets and to explain the impact of investor behaviour on asset price dynamics. My research extends current knowledge on investor networks by focusing on the identification of investor cliques to understand how different groups of investors (i.e. cliques) drive the market in certain direction. This research helps to understand the mechanism between investor behaviour and transitions in stock markets, an important information to identify early warning signal and detect market manipulation. Also, it justifies regulators to get a better access for investor level transaction data, such unique data set we use in this project, to plan effective policies. Moreover, information diffusion in financial markets is a fundamental question, which will be addressed by this research, especially focusing on information transfer between and within investor cliques. Methodologically, the project utilizes and develops clique enumeration techniques to identify network clusters. By analyzing the structure evolution of the investor multiplex networks and cliques, I am to detect if and how the structural changes are coupled between the different layers of the network and how the changes spread over all of the market. By using Vector Autoregression, inter-dependencies among multiple time series on investor networks and stock price processes can be identified with time-lagged influences. This computationally intensive research is implemented on a parallel computation platform. I use a unique data and massive investor registration data that allows me to track investors’ trading decisions over 20 years.

Оригинален текст от CORDIS (на английски).

Участници

TAMPEREEN KORKEAKOULUSAATIO SR · TampereКоординаторФинландия