DSpace Repository

Facilitate Business Process Design by Recommending Activities Vbased on Process Event Logs

Show simple item record

dc.contributor.advisor Dr. Matthew Dailey (Chairperson)
dc.contributor.author Yongsiriwit, Karn
dc.contributor.other Dr. Raphael Duboz (Member) Dr. Walid Gaaloul (External Member)
dc.date.accessioned 2015-01-28T06:34:51Z
dc.date.available 2015-01-28T06:34:51Z
dc.date.issued 2013-05
dc.identifier.other AIT Thesis no.CS-13-04 en_US
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/700
dc.description.abstract The rapidly changing of the business environment involves the flexible adaptation of business processes. It would not be efficient for companies to design or redesign their business processes without the consideration of design experiences, best practices, similar processes, etc. Many efforts have been made in the past decade to enhance the business process design, such as using available reference models based on requirements, or finding existing similar models to inspire a new process design. However, they are labor-intensive, errorprone, time-consuming and have sometimes NP-complexity graph matching problems. This thesis propose an approach to facilitate the design of business processes by recommending similar activities for selected activities. It examines process event logs, generates activity neighborhood contexts and compute the similarity between activities based on their neighborhood context matching. Process event logs exist in most information systems including CRM, ERP. Moreover, they represent the actual execution of the activities with the number of executed times. By capturing this knowledges from process event logs, we can effectively recommend activities to improve the process design. en_US
dc.description.sponsorship Royal Thai Government - AIT Fellowship en_US
dc.publisher AIT en_US
dc.title Facilitate Business Process Design by Recommending Activities Vbased on Process Event Logs en_US
dc.type Thesis en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account