A SHARED BRAIN FOR PEOPLE AND SOCIETY

Knowledge Graph Embeddings-based Explainable Artificial Intelligence for Enterprise Performance Management


Funded by 2021 National Science Foundation (NSF) Innovation Corps Grant

Voted by participants as #2 People's Choice Award

  • Project Overview

    Our project seeks to assess the fit between product/technology and its potential customer market, combining the outcomes from our participation at the NSF I-Corps Site program at UNCC Ventureprise in summer 2020 (Funding # 1450417) and research on visual analytics funded by two active NSF grants (the I/UCRC Site on Visual and Decision Informatics and an EAGER grant; Funding # 1747785 and # 1820862). 


    Our core technology is a knowledge graph embeddings-based platform for statistical and machine learning models of Enterprise Performance Management (EPM) data. We engage natural language processing models to convert a massive volume of scientific research in organizational science into a causal knowledge graph, which will be embedded into a visual analytics platform to structure and interpret enterprise management data. It helps EPM users to explain the hidden causal pathways visually and intuitively in their data related to organizational management and interventions.


    Keywords: Organizational performance, Organizational management, Stakeholders, Knowledge graph (KG)-embeddings, Explainable artificial intelligence (XAI), Visual analytics, Prescriptive analytics, Enterprise performance management (EPM)


  • Intellectual Merit

    Our core technology is a dynamic knowledge graph embeddings-based visual analytics platform on organizational performance for all stakeholders. The proposed technology combines our research outcomes across organizational and computer sciences, derived in part from the NSF I-Corps Site program as well as multiple works at the NSF I/UCRC Site. 


    The technology will combine two innovations. First, we have constructed, to our knowledge, the first scientific knowledge graph on causes-and-effects related to organizational performance. This knowledge graph was constructed by combining a novel, manually coded ontological hierarchy on organizational research and machine reading of the organizational science literature. 


    Second, we have developed a new knowledge graph embeddings-based visualization technique to enable explainable AI (XAI). We address the limitation of current AI using iterated matching between data and knowledge graph. We explicate the descriptions of variables in data and organize these descriptions using hierarchical clustering. Causal hypotheses are automatically developed based on the known causal links in the knowledge graph, and then empirically tested in statistical and machine learning models.

  • Broader Impacts

    We apply our technology in enterprise performance management (EPM) concerning all stakeholders (investors, customers, suppliers, employees, and the community). We make both knowledge advancement and societal/commercial impact. 


    First, we broaden the scope of knowledge from financial-centric performance to an interdisciplinary framework of economic, social, psychological, and physical well-being concerning all stakeholders. 


    Second, we democratize artificial intelligence (AI) to ordinary organizational managers who may not possess sophisticated analytics skills. The current AI models lack interactive and intuitive storytelling. Matching the hierarchical clustering of data with a causal knowledge graph, our proposed technology will prepare user data in a way that mimics a general manager’s intuitive thinking. 


    Third, we address the commercial gap in the market of lacking prescriptive capability, that is, telling end-users what they should do. Data may be collected from different sources in an organization, so they are fragmented and the causal links are lost. The external source of a causal knowledge graph fills the gap by presenting and interpreting the hidden causal links in EPM data, and thus helps executives to prescribe interventions such as the optimal level of causes to enhance the well-being of all stakeholders.

List of Services

List of Services

Share by: