TY - JOUR AU - Feblowitz, Mark AU - Hassanzadeh, Oktie AU - Katz, Michael AU - Sohrabi, Shirin AU - Srinivas, Kavitha AU - Udrea, Octavian PY - 2021/05/18 Y2 - 2024/03/28 TI - IBM Scenario Planning Advisor: A Neuro-Symbolic ERM Solution JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 18 SE - AAAI Demonstration Track DO - 10.1609/aaai.v35i18.18003 UR - https://ojs.aaai.org/index.php/AAAI/article/view/18003 SP - 16032-16034 AB - Scenario Planning is a commonly used Enterprise Risk Management(ERM) technique to help decision makers with longtermplans by considering multiple alternative futures. It istypically a manual, highly labor intensive process involvingdozens of experts and hundreds to thousands of person-hours.We previously introduced a Scenario Planning Advisor prototype(Sohrabi et al. 2018a,b) that focuses on generatingscenarios quickly based on expert-developed models. Wepresent the evolution of that prototype into a full-scale, cloud deployedERM solution that: (i) can automatically (throughNLP) create models from authoritative documents such asbooks, reports and articles, such that what typically took hundredsto thousands of person-hours can now be achieved inminutes to hours; (ii) can gather news and other feeds relevantto forces in the risk models and group them into storylineswithout any other user input; (iii) can generate scenariosat scale, starting with dozens of forces of interest from modelswith thousands of forces in seconds; (iv) provides interactivevisualizations of scenario and force model graphs, includinga full model editor in the browser.The SPA solution is deployed under a non-commercialuse license at https://spa-service.draco.res.ibm.comand includes a user guide to help new users getstarted. A video demonstration is available athttps://www.youtube.com/watch?v=IaX3d37NUl8. ER -