H2020Индивидуална стипендия2021–2022

QFRNA_SH · Quantitative Financial Risk Network Analysis with Sentiment and Herd Behaviour Measures

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

Период: 2021-01-01 → 2022-12-31
Финансиране от ЕС: 174 806 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Финансовите рискове и поведението на инвеститорите се анализират чрез нови математически методи, като например влиянието на слуховете върху цените на акциите в NASDAQ. Това помага за по-доброто разбиране на системните рискове и начина, по който хората следват поведението на другите.

Този кратък обзор е генериран от изкуствен интелект

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

Резултати накратко

Quantitative Financial Risk Network Analysis with Sentiment and Herd Behaviour Measures

The work carried out is interdisciplinary regarding econometrics, behavioural finance, text mining and machine learning. It is original for the development of new methods, such as an innovative FRM approach based on expectiles and a new business model to detect herd behavior. - "Financial Risk Meter FRM based on Expectiles" proposes an innovative method Financial Risk Meter (FRM) based on expectiles, which yields insight into the dynamics of network. The methodology was adopted in another paper "Tail Risk Network Effects in the Cryptocurrency Market during the COVID-19 Crisis" published in the Singapore Economic Review. An FRM website was built to show the daily FRM time series to indicate the dynamics of systemic risk. - "Peer Effects and Club Selections of a Unique Online Fishing Game" examines a unique large dataset in an online game setting to study the herd behavior, i.e., how a player's spending is influenced by other club members' purchasing behavior. We develop a three-step model that accounts for self-selection, reflection and overfitting issues to properly estimate peer effects. - "Buy on Rumor, Sell on News: the Effect of News Arrivals and Investor Sentiment on the Distribution of Excess Returns" analyses how the distribution of excess returns is influenced by investor opinion as investor sentiment and news arrivals by applying the expectile regression to a panel of 100 excess equity returns in NASDAQ over the period April 2015 - August 2019. When analyzing the effect of news and earnings announcements, we find a positive impact of the day before earnings announcements and a negative impact of news arrivals on low return expectiles. We explain this effect with the strategy “buy on rumor, sell on news” for low return states. - "Cross-exchange Crypto Risk: A High-frequency Dynamic Network Perspective" studies the dynamic crypto network. Cross-exchange trading induces risk spillover in the crypto market, especially for centralized exchanges, which compound crypto volatility and counterparty risk. We propose a Multivariate Heterogeneous AutoRegression for Crypto Market (MHAR-CM) to specifically investigate interconnectedness among 9 different exchanges on Bitcoin in a high-frequency resolution via dynamic partial correlation networks. To sum up, the grant aims at exploring network dynamics, quantifying investor sentiment and detecting herd behaviour to support decision-making and manage risks.

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

Цел на проекта

Sentiment drives the stock market (Shiller, 2000). Over-optimistic and over-pessimistic emotions can lead to great mispricing and excess volatility. The question is no longer whether investor sentiment affects stock prices, but rather how to measure investor sentiment and quantify its effects (Baker and Wurgler, 2007). (1) The proposal firstly plans to improve upon existing measures of investor sentiment by combining financial proxies and textual variables. Then it tries to calibrate the option-pricing model with the investor sentiment measure incorporated to achieve precise pricing. (2) While there has been much work on investor sentiment, there is a lacuna in research that explores sentiment network, in particular the interdependencies of the sentiment indices and their relationship with equity returns. The researcher aims to explore the interconnectedness of sentiment measures among different stocks and identifies which stock plays a crucial role by proposing an innovative semiparametric tail event driven network. (3) The interdependencies and co-movements of investor emotions may lead to herd behaviour in the financial market. One of the difficulties lies in differentiating between a rational reaction to changes in fundamental values and irrational herd behaviour. The proposal aims to detect and interpret the phenomenon considering macroeconomic signals, buy or sell transaction behaviour and investor sentiment. The overall proposal is, therefore, original not just because of employing new investor sentiment measures but for the development of new econometric methods in the first place. Moreover, it potentially contributes to inclusive, innovative and reflective societies in Europe by supporting financial decision-making processes and managing risks for investors and institutions.

Оригинален текст от CORDIS (на английски).

Участници

HUMBOLDT-UNIVERSITAET ZU BERLIN · BerlinКоординаторГермания