Financial markets react in different ways to economic shocks. Today is very important to understand and study different financial markets reaction to external shocks in order to find continuous patterns and rules for future forecasts. This thesis provides a novel approach to the analysis of markets reaction to shocks whose origin is different, taking also into account the sectors composition of indexes. Using Pearson correlation networks and complex network measures, I find evidence of different responses to crises from the American and Japanese markets. These findings are then confirmed with a node embedding and clustering analysis done on the correlation networks obtained
I mercati finanziari reagiscono in modi diversi agli shock economici. Oggi è molto im portante capire e studiarela reazione di diversi mercati finanziari a shock esterni in modo tale da riuscire a trovare delle analogie e regole per poter effettuare delle previsioni per il futuro. Questa tesi fornisce un approccio innovativo per quanto riguarda l’analisi delle reazioni dei mercati a crisi la cui causa è diversa, prendendo in considerazione anche la composizione degli indici in settori. Usando le reti di correlazione di Pearson e delle misure di complessità delle reti, trovo evidenza di risposte diverse alle crisi da parte dei mercati americano e giapponese. Queste scoperte sono ulteriormente confermate con un’analisi di node embedding e clustering effettuate sulle reti di correlazione ottenute.
Financial markets reaction to recent crises: a novel approach involving node embeddings and clustering techniques
Marcosignori, Lucrezia
2021/2022
Abstract
Financial markets react in different ways to economic shocks. Today is very important to understand and study different financial markets reaction to external shocks in order to find continuous patterns and rules for future forecasts. This thesis provides a novel approach to the analysis of markets reaction to shocks whose origin is different, taking also into account the sectors composition of indexes. Using Pearson correlation networks and complex network measures, I find evidence of different responses to crises from the American and Japanese markets. These findings are then confirmed with a node embedding and clustering analysis done on the correlation networks obtainedFile | Dimensione | Formato | |
---|---|---|---|
Thesis_Lucrezia_Marcosignori.pdf
non accessibile
Dimensione
10.38 MB
Formato
Adobe PDF
|
10.38 MB | Adobe PDF | Visualizza/Apri |
Executive_Summary__Lucrezia Marcosignori.pdf
non accessibile
Descrizione: executive summary
Dimensione
380.03 kB
Formato
Adobe PDF
|
380.03 kB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/197993