Version 1
: Received: 18 May 2022 / Approved: 19 May 2022 / Online: 19 May 2022 (15:25:11 CEST)
How to cite:
Leogrande, A.; Magaletti, N.; Cosoli, G.; Giardinelli, V.; Massaro, A. The Determinants of Internet User Skills in Europe. Preprints2022, 2022050263. https://doi.org/10.20944/preprints202205.0263.v1
Leogrande, A.; Magaletti, N.; Cosoli, G.; Giardinelli, V.; Massaro, A. The Determinants of Internet User Skills in Europe. Preprints 2022, 2022050263. https://doi.org/10.20944/preprints202205.0263.v1
Leogrande, A.; Magaletti, N.; Cosoli, G.; Giardinelli, V.; Massaro, A. The Determinants of Internet User Skills in Europe. Preprints2022, 2022050263. https://doi.org/10.20944/preprints202205.0263.v1
APA Style
Leogrande, A., Magaletti, N., Cosoli, G., Giardinelli, V., & Massaro, A. (2022). The Determinants of Internet User Skills in Europe. Preprints. https://doi.org/10.20944/preprints202205.0263.v1
Chicago/Turabian Style
Leogrande, A., Vito Giardinelli and Alessandro Massaro. 2022 "The Determinants of Internet User Skills in Europe" Preprints. https://doi.org/10.20944/preprints202205.0263.v1
Abstract
The following article indicates the determinants of “Internet User Skills” among European countries based on the application of the database deriving from the DESI-Index. The data were analyzed using the following econometric models, namely: Panel Data with Fixed Effects, Panel Data with Random Effects, Pooled OLS, WLS, WLS corrected for heteroskedasticity. The Elbow method and the Silouette coefficient method were compared for the optimization of the number of clusters obtained by the k-Means algorithm. The result shows the presence of 5 clusters. A network analysis was carried out using the Euclidean distance with the result of identifying two network structures between some analyzed countries. subsequently a comparison was made between six different machine learning algorithms for the prediction of the future value of the variable of interest. The result shows that the best predictor algorithm is Gradient Boosted Tree Regression with an expected value of the predicted variable increasing by a value of 1.75%. Later a further comparison was made by comparing 6 algorithms with the increased data. The result shows that the best predictor is Simple Regression Tree. The interest variable is predicted to decrease by an amount equal to -6.099%. Statistical errors improve on average by 32.43% in the transition between the original data and the increased data.
Keywords
Innovation and Invention; Processes and Incentives; Management of Technological Innovation and R&D; Diffusion Processes; Open Innovation
Subject
Business, Economics and Management, Economics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.