This study analyses a financial database for a sample of medium-sized family (FB) and non-family (NFB) businesses located in the Central District of Italy, observed in 2007, 2009 and 2014, as to say: before, during and after the spreading of the global crisis wave. Data have been analysed in a quantitative way with a Machine Learning tool (namely: Self Organizing Maps- SOMs) trained on data. This choice depends on the fact that SOMs is a well-known technique to explore data and to extract clusters based on their intrinsic features, letting -literally- the data to speak for themselves. The aim of this study is twofold. First, we are aimed to check medium-sized firms’ ability to adapt to changing economic conditions and to understand whether during the recent economic crisis medium-sized FBs’ performance followed a particular trend. Second, we investigate to what extent the SOM is able to extract relevant patterns of information in the given dataset. Experimental results demonstrate the potential of the suggested approach and define the trail for further investigations.

Family Businesses, Innovation and Performance During an Economic Crisis: The SOM Methodology

Cesaroni Francesca M.;Sentuti Annalisa
2017-01-01

Abstract

This study analyses a financial database for a sample of medium-sized family (FB) and non-family (NFB) businesses located in the Central District of Italy, observed in 2007, 2009 and 2014, as to say: before, during and after the spreading of the global crisis wave. Data have been analysed in a quantitative way with a Machine Learning tool (namely: Self Organizing Maps- SOMs) trained on data. This choice depends on the fact that SOMs is a well-known technique to explore data and to extract clusters based on their intrinsic features, letting -literally- the data to speak for themselves. The aim of this study is twofold. First, we are aimed to check medium-sized firms’ ability to adapt to changing economic conditions and to understand whether during the recent economic crisis medium-sized FBs’ performance followed a particular trend. Second, we investigate to what extent the SOM is able to extract relevant patterns of information in the given dataset. Experimental results demonstrate the potential of the suggested approach and define the trail for further investigations.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11576/2654536
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact