 |
International Society of Science and Applied Technologies |
| Post-COVID Recovery and Predictive Analytics: Technical Challenges | ||||
| Author | Brady McMicken
|
|||
| Co-Author(s) | Mike Sturdevant; Andrei Shcheprov; Alan Cordell
|
|||
| Abstract | Despite tremendous advances in the development of Machine Learning and Artificial Intelligence frameworks, significant technical challenges remain in dealing with the impact of pervasive, persistent, and pronounced onetime events such as COVID-19. Due to very abnormal social and economic behaviors that occurred in 2020-2021 across the globe, many businesses experienced dramatic changes in business outcomes during the COVID period. Coming out of this period, many businesses experienced a follow-on recovery period where business outcomes changed once again as society began to return to its prior state. This post-COVID state did not match either the pre- COVID or COVID period. In such an environment, a key question that needed to be answered was what if any long-term changes to the business outcomes could be forecasted given the trends and patterns learned from the pre-COVID, COVID and post-COVID business outcomes. The paper aims to review these questions and present a vision care business use case to illustrate several practical steps to address the above situation.
|
|||
| Keywords | machine learning, business analytics, time series analysis, neural network | |||
| Article #: RQD2024-41 | ||||
Proceedings of 29th ISSAT International Conference on Reliability & Quality in Design |