Modeling Sustainability Reporting with Ternary Attractor Neural Networks
This work models the Corporate Sustainability General Reporting Initiative (GRI) using a ternary attractor network. A dataset of 15 years evolution of the GRI reports for a world-wide set of companies was compiled from a recent work and adapted to match the pattern coding for a ternary attractor network. We compare the performance of the network with a classical binary attractor network. Two types of criteria were used for encoding the ternary network, i.e., a simple and weighted threshold, and the performance retrieval was better for the latter, highlighting the importance of the real patterns’ transformation to the three-state coding. The network exceeds the retrieval performance of the binary network for the chosen correlated patterns (GRI). Finally, the ternary network was proved to be robust to retrieve the GRI patterns with initial noise.
KeywordsSustainability Ternary coding Bi-linear and Bi-quadratic retrieval
This work has been supported by Spanish grants MINECO (http://www.mineco.gob.es/) TIN2014-54580-R, TIN2017-84452-R, and by UAM-Santander CEAL-AL/2017-08, and UDLA-SIS.MG.17.02.
- 12.GRI: GRI sustainability reporting standards (2018). https://www.globalreporting.org/Pages/default.aspx
- 17.Shahi, A., Issac, B., Modapothala, J.: Intelligent corporate sustainability report scoring solution using machine learning approach to text categorization. In: 2012 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology (STUDENT), pp. 227–232 (2012)Google Scholar