Speakers‎ > ‎

Recommendation driven economic complexity enhancement method

Author: Hao Liao


Prediction is one of the major challenges in complex systems. Prediction methods can help policy makers to solve practical problems successfully and make better strategy for the future. This work is divided into two parts: the first is to study three different methods characterizing the complex networks and compare their predictive ability on GDP. The second is using recommendation system to recommend products which are neglected for exporting countries in their production capacity.  In addition, we apply the Fitness and Complexity metrics to verify the results of recommendation and we simulate the evolution in country's fitness after exporting the recommended products. The purpose of this work is combining these two methods to help exporting countries improve national competitiveness, especially for developing countries.

Figure 1: Panel (a) and (b) are comparisons of Recall and Precision for the five algorithms. The recommendation is performed at year T for year T+5, with T ranging from year 2001 to 2010. The results shown are averaged over this time period. Countries are divided into three different tiers according to their fitness rank. Panel (c) is the average increase of fitness ranking for the three different tiers of countries for the time period 2008-2015.