Location
Hilton Hawaiian Village, Honolulu, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2024 12:00 AM
End Date
6-1-2024 12:00 AM
Description
While anecdotal evidence highlights the value of Internet-of-Things (IoT) data for business operations, rigorous empirical validation is still limited. The key challenge lies in integrating IoT analytics into business evaluation. To address the issues, we focus on the automotive industry and study the value of telematics data, an important IoT application in this domain, in terms of predicting maintenance, repair, and operations (MRO) service demands. Our approach involves building a prediction system with users’ driving behavior, MRO service records, and environmental data (weather and traffic). We show a substantial improvement in prediction performance upon incorporating user behavior information derived from IoT data. Specifically, we find that hard acceleration, hard braking, and speeding rank the third, fifth, and sixth, respectively, in terms of their contribution to the MRO prediction. Our results shed light on the design of product-service systems (PSS), an emerging trend to integrate product offerings with service offerings.
Recommended Citation
Zhang, Jieyi; Yang, Cenying; and Feng, Yihao, "Demand Prediction by Incorporating Internet-of-Things Data: A Case of Automobile Repair and Maintenance Service" (2024). Hawaii International Conference on System Sciences 2024 (HICSS-57). 2.
https://aisel.aisnet.org/hicss-57/in/internet_of_everything/2
Demand Prediction by Incorporating Internet-of-Things Data: A Case of Automobile Repair and Maintenance Service
Hilton Hawaiian Village, Honolulu, Hawaii
While anecdotal evidence highlights the value of Internet-of-Things (IoT) data for business operations, rigorous empirical validation is still limited. The key challenge lies in integrating IoT analytics into business evaluation. To address the issues, we focus on the automotive industry and study the value of telematics data, an important IoT application in this domain, in terms of predicting maintenance, repair, and operations (MRO) service demands. Our approach involves building a prediction system with users’ driving behavior, MRO service records, and environmental data (weather and traffic). We show a substantial improvement in prediction performance upon incorporating user behavior information derived from IoT data. Specifically, we find that hard acceleration, hard braking, and speeding rank the third, fifth, and sixth, respectively, in terms of their contribution to the MRO prediction. Our results shed light on the design of product-service systems (PSS), an emerging trend to integrate product offerings with service offerings.
https://aisel.aisnet.org/hicss-57/in/internet_of_everything/2