Which products activate a product? An explainable machine learning approach

TL;DR

This paper introduces a statistically validated, explainable machine learning approach to identify key products that influence a country's ability to export a target product, improving interpretability and forecasting accuracy.

Contribution

It proposes a method to validate product importance in export feasibility assessments, creating an interpretable feature space and revealing correlations between product complexities.

Findings

Identified products that significantly increase export probability.

Developed a low-dimensional, interpretable feature space.

Found a positive correlation between product complexity and its explainers.

Abstract

Tree-based machine learning algorithms provide the most precise assessment of the feasibility for a country to export a target product given its export basket. However, the high number of parameters involved prevents a straightforward interpretation of the results and, in turn, the explainability of policy indications. In this paper, we propose a procedure to statistically validate the importance of the products used in the feasibility assessment. In this way, we are able to identify which products, called explainers, significantly increase the probability to export a target product in the near future. The explainers naturally identify a low dimensional representation, the Feature Importance Product Space, that enhances the interpretability of the recommendations and provides out-of-sample forecasts of the export baskets of countries. Interestingly, we detect a positive correlation between the complexity of a product and the complexity of its explainers.