The relatedness between an economic actor (for instance a country, or a firm) and a product is a measure of the feasibility of that economic activity. As such, it is a driver for investments both at a private and institutional level. Traditionally, relatedness is measured using complex networks approaches derived by country-level co-occurrences. In this work, we compare complex networks and machine learning algorithms trained on both country and firm-level data. In order to quantitatively compare the different measures of relatedness, we use them to predict the future exports at country and firm-level, assuming that more related products have higher likelihood to be exported in the near future. Our results show that relatedness is scale-dependent: the best assessments are obtained by using machine learning on the same typology of data one wants to predict. Moreover, while relatedness measures based on country data are not suitable for firms, firm-level data are quite informative also to predict the development of countries. In this sense, models built on firm data provide a better assessment of relatedness with respect to country-level data. We also discuss the effect of using community detection algorithms and parameter optimization, finding that a partition into a higher number of blocks decreases the computational time while maintaining a prediction performance that is well above the network based benchmarks.
翻译:经济行为者(例如一个国家或公司)与产品之间的联系是衡量这种经济活动可行性的一个尺度。因此,它是私人和机构一级投资的驱动力。传统上,关联性是通过国家一级共同发生的复杂网络方法衡量的。在这项工作中,我们比较了在国家和公司一级数据方面受过训练的复杂网络和机器学习算法。为了从数量上比较不同的关联度量,我们用它们来预测国家和公司一级的未来出口量,假设更多的相关产品在近期内出口的可能性更大。我们的结果显示,关联性取决于规模:最佳评估是通过利用机器学习所要预测的数据类型来获得的。此外,虽然基于国家数据的相关度措施不适合公司,但公司一级数据也非常丰富,可以预测国家的发展。从这个意义上讲,根据公司数据建立的模式可以更好地评估与国家一级数据的关系。我们还讨论了使用社区检测算法和参数优化在近期内的影响。我们发现,使用社区检测算法和参数优化是取决于规模的:最佳评估是通过对所要预测的数据的同一类型进行机器学习获得的。此外,虽然基于国家数据的有关程度的计量措施不适合于公司,但公司一级数据也非常有助于预测国家的发展。从高水平上计算。