Edasijõudnud meetodid äriprotsesside hälbe kaevandamiseks
Files
Date
2019
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Äriprotsessi hälve on nähtus, kus alamhulk äriprotsessi täitmistest erinevad soovitud või ettenähtud tulemusest, kas positiivses või negatiivses mõttes. Äriprotsesside hälbega täitmised sisaldavad endas täitmisi, mis ei vasta ettekirjutatud reeglitele või täitmised, mis on jäävad alla või ületavad tulemuslikkuse eesmärke. Hälbekaevandus tegeleb hälbe põhjuste otsimisega, analüüsides selleks äriprotsesside sündmuste logisid.Antud töös lähenetakse protsessihälvete põhjuste otsimise ülesandele, esmalt kasutades järjestikkudel põhinevaid või deklaratiivseid mustreid ning nende kombinatsiooni. Hälbekaevandusest saadud põhjendusi saab parendada, kasutades sündmustes ja sündmusjälgede atribuutides sisalduvaid andmelaste. Andmelastidest konstrueeritakse uued tunnused nii otsekoheselt atribuute ekstraheerides ja agregeerides kui ka andmeteadlike deklaratiivseid piiranguid kasutades. Hälbeid iseloomustavad põhjendused ekstraheeritakse kasutades kaudset ja otsest meetodit reeglite induktsiooniks. Kasutades sünteetilisi ja reaalseid logisid, hinnatakse erinevaid tunnuseid ja tulemuseks saadud otsustusreegleid nii nende võimekuses täpselt eristada hälbega ja hälbeta protsesside täitmiseid kui ka kasutajatele antud lõpptulemustes.
Business process deviance refers to the phenomenon whereby a subset of the executions of a business process deviate, in a negative or positive way, with respect to its expected or desirable outcomes. Deviant executions of a business process include those that violate compliance rules, or executions that undershoot or exceed performance targets. Deviance mining is concerned with uncovering the reasons for deviant executions by analyzing business process event logs. In this thesis, the problem of explaining deviations in business processes is first investigated by using features based on sequential and declarative patterns, and a combination of them. The explanations are further improved by leveraging the data payload of events and traces in event logs through features based on pure data attribute values and data-aware declare constraints. The explanations characterizing the deviances are then extracted by direct and indirect methods for rule induction. Using synthetic and real-life logs from multiple domains, a range of feature types and different forms of decision rules are evaluated in terms of their ability to accurately discriminate between non-deviant and deviant executions of a process as well as in terms of the final outcome returned to the users.
Business process deviance refers to the phenomenon whereby a subset of the executions of a business process deviate, in a negative or positive way, with respect to its expected or desirable outcomes. Deviant executions of a business process include those that violate compliance rules, or executions that undershoot or exceed performance targets. Deviance mining is concerned with uncovering the reasons for deviant executions by analyzing business process event logs. In this thesis, the problem of explaining deviations in business processes is first investigated by using features based on sequential and declarative patterns, and a combination of them. The explanations are further improved by leveraging the data payload of events and traces in event logs through features based on pure data attribute values and data-aware declare constraints. The explanations characterizing the deviances are then extracted by direct and indirect methods for rule induction. Using synthetic and real-life logs from multiple domains, a range of feature types and different forms of decision rules are evaluated in terms of their ability to accurately discriminate between non-deviant and deviant executions of a process as well as in terms of the final outcome returned to the users.