WIBISONO, ARIF and NISAFANI, AMNA SHIFIA and Hyerim Bae, Hyerim Bae and You-Jin Park, You-Jin Park (2016) A DYNAMIC AND HUMAN-CENTRIC RESOURCE ALLOCATION FOR MANAGING BUSINESS PROCESS EXECUTION. International Journal of Industrial Engineering: Theory, Applications and Practice, 23(4), 2016. ISSN 1943-670X
Preview |
Text
198303062012121001_dynamic_wibisono.pdf - Published Version Download (794kB) | Preview |
Abstract
Generally, resource allocation is essential to the efficient operational execution. More specifically, resource allocation for semi-automatic business processes might be more sophisticated due to human involvement. To this point, human performances are oscillating over time. Hence, upfront and static resource allocation might be suboptimal to deal with human dynamics. For this reason, this research suggests a dynamic and human-centric resource allocation to organize human-type resources in semi-automatic business process. Here, we use Bayesian approaches to predict resource’s performances according to historical data set. As a result, we can construct a dynamic priority rule to assign a job to a specific resource with the highest probability to work faster. Finally, we demonstrate that our approach outperforms other priority rules: Random, Lowest Idle, Highest Idle, Order, and previously developed Bayesian Selection Rule from the total completion time and waiting time point of view.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | dynamic resource allocation, machine learning, dynamic dispatching rule, dynamic priority rule, naïve bayes |
Subjects: | Z Bibliography. Library Science. Information Resources > ZA Information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources |
Divisions: | Faculty of Information Technology > Information System |
Depositing User: | Users 13 not found. |
Date Deposited: | 24 Jan 2017 08:55 |
Last Modified: | 27 Dec 2018 08:32 |
URI: | http://repository.its.ac.id/id/eprint/3062 |
Actions (login required)
View Item |