Agriculture and food production could be an engine of economic growth in a lot of countries. The obvious way to force food and agriculture development is to discover new foreign markets with high probability of growth in the nearest future. The objective of this study is to reveal combinations of commodities and partner countries for which persistent growth of export value is expected. The proposed framework uses open data about international trade flows and production from United Nations, International Monetary Found, weather databases and quantile regression models based on neural networks. The experiments show that considering retrospective data allows to accurate forecast the desired combinations.
DOI: http://dx.doi.org/10.1109/IS.2018.8710561
PDF на IEEE Xplore (на англ.): https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8710561
Скопус: http://www.scopus.com/inward/record.url?scp=85065967127&partnerID=8YFLogxK
ResearchGate: https://www.researchgate.net/publication/332996480_Neural_Networks_for_Food_Export_Gain_Forecasting
Semantic Scholar: https://api.semanticscholar.org/CorpusID:148573542
Devyatkin D. et al. Neural Networks for Food Export Gain Forecasting // 2018 International Conference on Intelligent Systems (IS). – IEEE, 2018. – p. 312-317.