Product progression: a machine learning approach to forecasting industrial upgrading
Abstract Economic complexity methods, and in particular relatedness measures, lack a systematic evaluation and comparison framework. We argue that out-of-sample forecast exercises should play this role, and we compare various machine learning models to set the prediction benchmark. We find that the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-28179-x |
| _version_ | 1811175907922018304 |
|---|---|
| author | Giambattista Albora Luciano Pietronero Andrea Tacchella Andrea Zaccaria |
| author_facet | Giambattista Albora Luciano Pietronero Andrea Tacchella Andrea Zaccaria |
| author_sort | Giambattista Albora |
| collection | DOAJ |
| description | Abstract Economic complexity methods, and in particular relatedness measures, lack a systematic evaluation and comparison framework. We argue that out-of-sample forecast exercises should play this role, and we compare various machine learning models to set the prediction benchmark. We find that the key object to forecast is the activation of new products, and that tree-based algorithms clearly outperform both the quite strong auto-correlation benchmark and the other supervised algorithms. Interestingly, we find that the best results are obtained in a cross-validation setting, when data about the predicted country was excluded from the training set. Our approach has direct policy implications, providing a quantitative and scientifically tested measure of the feasibility of introducing a new product in a given country. |
| first_indexed | 2024-04-10T19:44:43Z |
| format | Article |
| id | doaj.art-e7f1af82f1a64730b1b46a6b192790d8 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-10T19:44:43Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-e7f1af82f1a64730b1b46a6b192790d82023-01-29T12:09:16ZengNature PortfolioScientific Reports2045-23222023-01-0113111710.1038/s41598-023-28179-xProduct progression: a machine learning approach to forecasting industrial upgradingGiambattista Albora0Luciano Pietronero1Andrea Tacchella2Andrea Zaccaria3Dipartimento di Fisica, Universitá SapienzaCentro Ricerche Enrico FermiJoint Research CentreCentro Ricerche Enrico FermiAbstract Economic complexity methods, and in particular relatedness measures, lack a systematic evaluation and comparison framework. We argue that out-of-sample forecast exercises should play this role, and we compare various machine learning models to set the prediction benchmark. We find that the key object to forecast is the activation of new products, and that tree-based algorithms clearly outperform both the quite strong auto-correlation benchmark and the other supervised algorithms. Interestingly, we find that the best results are obtained in a cross-validation setting, when data about the predicted country was excluded from the training set. Our approach has direct policy implications, providing a quantitative and scientifically tested measure of the feasibility of introducing a new product in a given country.https://doi.org/10.1038/s41598-023-28179-x |
| spellingShingle | Giambattista Albora Luciano Pietronero Andrea Tacchella Andrea Zaccaria Product progression: a machine learning approach to forecasting industrial upgrading Scientific Reports |
| title | Product progression: a machine learning approach to forecasting industrial upgrading |
| title_full | Product progression: a machine learning approach to forecasting industrial upgrading |
| title_fullStr | Product progression: a machine learning approach to forecasting industrial upgrading |
| title_full_unstemmed | Product progression: a machine learning approach to forecasting industrial upgrading |
| title_short | Product progression: a machine learning approach to forecasting industrial upgrading |
| title_sort | product progression a machine learning approach to forecasting industrial upgrading |
| url | https://doi.org/10.1038/s41598-023-28179-x |
| work_keys_str_mv | AT giambattistaalbora productprogressionamachinelearningapproachtoforecastingindustrialupgrading AT lucianopietronero productprogressionamachinelearningapproachtoforecastingindustrialupgrading AT andreatacchella productprogressionamachinelearningapproachtoforecastingindustrialupgrading AT andreazaccaria productprogressionamachinelearningapproachtoforecastingindustrialupgrading |