In this work, we explore the application of machine learning models (MLM) to the analysis of firms’ performance. To such aim, we consider a bunch of financial indicators on firms operating in the Information and Communication Technology (ICT) sector, with attention to enterprises providing ICT related-services. The rationale is to highlight the potential of MLM to exploit the complexity of financial data, and to offer a handy way to visualize the related information. In fact, instead of performing classical analysis, we discuss how to apply to those indicators Self-Organizing Maps-SOMs—that are well suited to manage high dimensional and complex datasets to extract their relevant features. It emerges that SOMs are useful in clustering companies depending on multi-dimensional criteria and in analysing hidden relations in companies’ performances.

Mapping financial performances in Italian ICT-related firms via self-organizing maps

Resta, Marina;Garelli, Roberto;Dameri, Renata Paola
2018-01-01

Abstract

In this work, we explore the application of machine learning models (MLM) to the analysis of firms’ performance. To such aim, we consider a bunch of financial indicators on firms operating in the Information and Communication Technology (ICT) sector, with attention to enterprises providing ICT related-services. The rationale is to highlight the potential of MLM to exploit the complexity of financial data, and to offer a handy way to visualize the related information. In fact, instead of performing classical analysis, we discuss how to apply to those indicators Self-Organizing Maps-SOMs—that are well suited to manage high dimensional and complex datasets to extract their relevant features. It emerges that SOMs are useful in clustering companies depending on multi-dimensional criteria and in analysing hidden relations in companies’ performances.
2018
978-3-319-62635-2
978-3-319-62636-9
File in questo prodotto:
File Dimensione Formato  
dameri_garelli_resta_springer.pdf

accesso chiuso

Tipologia: Documento in versione editoriale
Dimensione 482.09 kB
Formato Adobe PDF
482.09 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/901235
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact