The goal of this paper is using Neural Networks (NN) to analyze business performance and support small territories development policies. The contribution of the work to the existing literature may be basically summarized as follows: we are focusing on the application of an unsupervised neural network (namely: on Self-Organizing Maps –SOM) to discover firms clusters on micro-territories inside city’s boundaries, and to exploit possible development policies at local level. Although since early ’90 of the past century NN have been widely employed to evaluate firms performance, to the best of our knowledge the use of SOM of that specific task is much less documented. Moreover, the main novelty of the paper relies on the attention to data at “microscopic” level: data processing in an infra-city perspective, in fact, has been neglected till now, although recent studies demonstrate that inequalities in economic and well-being conditions of people are higher among neighbourhoods of the same city rather than among different cities or regions. The performance analysis of a large set (7000 environ) of companies settled in Genova, Italy permits to test our research method and to design further applications to a large spectrum of territorial surveys regarding both economic and social well-being conditions.

Unsupervised neural networks for the analysis of business performance at infra-city level

DAMERI, RENATA;GARELLI, ROBERTO;RESTA, MARINA
2016-01-01

Abstract

The goal of this paper is using Neural Networks (NN) to analyze business performance and support small territories development policies. The contribution of the work to the existing literature may be basically summarized as follows: we are focusing on the application of an unsupervised neural network (namely: on Self-Organizing Maps –SOM) to discover firms clusters on micro-territories inside city’s boundaries, and to exploit possible development policies at local level. Although since early ’90 of the past century NN have been widely employed to evaluate firms performance, to the best of our knowledge the use of SOM of that specific task is much less documented. Moreover, the main novelty of the paper relies on the attention to data at “microscopic” level: data processing in an infra-city perspective, in fact, has been neglected till now, although recent studies demonstrate that inequalities in economic and well-being conditions of people are higher among neighbourhoods of the same city rather than among different cities or regions. The performance analysis of a large set (7000 environ) of companies settled in Genova, Italy permits to test our research method and to design further applications to a large spectrum of territorial surveys regarding both economic and social well-being conditions.
File in questo prodotto:
File Dimensione Formato  
Dameri2016_Chapter_UnsupervisedNeuralNetworksForT.pdf

accesso chiuso

Tipologia: Documento in versione editoriale
Dimensione 323.27 kB
Formato Adobe PDF
323.27 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/11567/772909
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact