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, M.;Dameri, R. P.;Garelli, R.
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.File | Dimensione | Formato | |
---|---|---|---|
Resta2018_Chapter_MappingFinancialPerformancesIn.pdf
accesso chiuso
Tipologia:
Documento in versione editoriale
Dimensione
415.58 kB
Formato
Adobe PDF
|
415.58 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.