Analyzing Regional Disparities in E-Commerce Adoption Among Italian SMEs - Integrating Machine Learning Clustering and Predictive Models with Econometric Analysis - November 2024

Aug 5, 2026

Upload by Aria

The study investigates how Italian SMEs with at least ten employees adopt e-commerce tools while accounting for regional inequalities and providing evidence relevant to economic policy. Using ISTAT-BES data, it applies k-means clustering optimized through silhouette and elbow diagnostics to uncover regional groupings, and estimates panel econometric models including fixed and random effects, weighted least squares, and dynamic panels. Findings indicate positive links between e-commerce activity and factors such as cultural and creative employment and regular internet use, alongside negative associations with household computer and internet availability. It also compares machine learning methods to predict future e-commerce adoption trends.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages61

Reading Time2 h 34 min

AccessFree to download

Abstract

Introduction

Research question and scope

Methodology overview

Munich Personal RePEc Archive Analyzing Regional Disparities in E-Commerce Adoption Among Italian SMEs: Integrating Machine Learning Clustering and Predictive Models with Econometric Analysis Leogrande, Angelo and Drago, Carlo and Arnone, Massimo LUM Unversity Giuseppe Degennaro, Unicusano University, Italian Courty of Auditors November 2024 Online at [https://mpra. ub. uni-muenchen. de/122115/](https://mpra. ub. uni-muenchen. de/122115/) [MPRA Paper No. 122115](MPRA Paper No. 122115) , [posted 23 Sep 2024 13:31 UTC](posted 23 Sep 2024 13:31 UTC) Analyzing Regional Disparities in E-Commerce Adoption Among Italian SMEs: Integrating Machine Learning Clustering and Predictive Models with Econometric Analysis Angelo Leogrande ^, Carlo Drago°, Massimo Arnone ^LUM University Giuseppe Degennaro [leogrande.cultore@lum.it](leogrande.cultore@lum.it)[ ](leogrande.cultore@lum.it)°Associate Professor at Niccolò Cusano University, [carlo.drago@unicusano.it](carlo.drago@unicusano.it)[ ](carlo.drago@unicusano.it)*Researcher University of Catania, Department of Economics and Business [massimo.arnone@unict.it](massimo.arnone@unict.it) Abstract The article explores the diffusion of online sales tools among Italian enterprises with at least ten employees, considering regional inequalities through methods that help address economic policy. The study gives an overall assessment of the adoption of e-commerce among Italian SMEs, using multiple methods that help to identify regional disparities and provide insight for policymakers. The data were obtained from the ISTAT-BES database. Analysis was applied using the k-Means machine learning algorithm by comparing the Silhouette coefficient vs. the Elbow method. The elbow method reveals greater expository capacity, and the optimal number of clusters equals 3. The econometric analysis used the following methods: Panel Data with Fixed Effects, Panel Data with Random Effects, Weighted Least Squares-WLS, and Dynamic Panels at 1 Stage. The results show that cultural and creative employment and regular internet users are positively associated with SMEs active in ecommerce while negatively associated with the family's availability of at least one computer and internet connection. Finally, the article compares different machine learning algorithms to predict the future value of SMEs active in e-commerce. The results are discussed critically. JEL CODE: O3, O31, O32, O33, O34 Keywords: e-Commerce, Small and Medium Enterprises, Regional Inequalities, Panel Data, kMeans, Machine-Learning. 1. Introduction The article mainly focuses on regional differences, unveiling the socioeconomic and technological factors determining e-commerce adoption by comparing the Italian regions. Besides, it determines the effectiveness of agglomerative algorithms with k-means clustering, optimized with the silhouette coefficient and elbow method, on patterns and grouping by regions. In contrast, based on panel econometric models, the former examines technological and innovative determinants fostering the adoption of e-commerce. Further, there is an examination of the comparison among different machine learning algorithms in forecasting the future trend of e-commerce adoption and rounds off with the policy recommendations for the economic policy measures of the future. (Polenzani, et al., 2021; Gherghina et al., 2021; Belisari et al., 2020). The article's methodology is relevant, attractive, and innovative and covers the comprehensiveness of analysis regarding e-commerce adoption among Italian SMEs from different regions. The article involves an analytical technique with static analysis, clustering with algorithms like k-Means optimized with the Silhouette Coefficient and the Elbow Method, panel econometric modeling, and comparisons between various machine learning algorithms to predict future trends. With these techniques, it will be possible to obtain a comprehensive view of the phenomenon from the distribu

FAQs

What data and company scope does the study use to analyze e-commerce adoption in Italy?

The analysis focuses on Italian enterprises with at least ten employees and uses data from the ISTAT-BES database.

How does the paper determine the clustering structure for regional disparities?

It applies the k-means algorithm and evaluates solutions using the Silhouette coefficient and the Elbow method, concluding that the optimal number of clusters is 3.

Which econometric approaches are used, and what key associations are reported?

The econometric analysis includes panel fixed effects, panel random effects, weighted least squares (WLS), and dynamic panels at 1 stage. Results report positive associations with cultural and creative employment and regular internet users, and negative associations with household availability of at least one computer and an internet connection for SMEs active in e-commerce.

Aug 5, 2026

Upload by Aria