Back to Search Start Over

Development of Intelligent Robotic Process Automation: A Utility Case Study in Brazil

Authors :
Gustavo Matheus de Almeida
John A. R. Bedoya
Bruna Vajgel
Thais Tossoli De Sousa
Vanessa Rafaela de S. Demuner
Rosa Virginia Encinas Quille
Pedro Luiz Pizzigatti Corrêa
Lucia Vilela Leite Filgueiras
Denis Mollica
Source :
IEEE Access, Vol 9, Pp 71222-71235 (2021)
Publication Year :
2021
Publisher :
Institute of Electrical and Electronics Engineers (IEEE), 2021.

Abstract

Robotic Process Automation (RPA) refers to process automation applications of traditional Information Technologies based on robot software with the ability to capture and interpret the specific processes of organizations. Studies show that RPAs are able to reduce resources and optimize processes effectively in relation to customers. Some of these call center business processes deal with customers most likely to complain; therefore, a “Proactive Notification” robot was developed to classify these types of customers to be prioritized. This robot defines the creation of an RPA architecture for proactive notifications applied to an electric company in Brazil. The methodology used for the development of this project consisted of data management, predictive models, and peripheral components for sending SMS and making calls. It was tested against all customers in 40 cities (two states) and the model considers the historical basis of 3 years of occurrences to predict customers with a high probability of filing a complaint due to power failure. The results show that customers who were called for this type of problem did not call the call center again to complain, suggesting positive acceptance of the robot. In conclusion, the robot presented herein is capable of making proactive notifications with high precision to customers with the highest probability of complaints, predicting possible problems.

Details

ISSN :
21693536
Volume :
9
Database :
OpenAIRE
Journal :
IEEE Access
Accession number :
edsair.doi.dedup.....140e1352b3a70b869eb8597191d61956
Full Text :
https://doi.org/10.1109/access.2021.3075693