Predictive and prescriptive monitoring of business process outcomes
Date
2019-03-14
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Viimastel aastatel on erinevates valdkondades tegutsevad ettevõtted üles näidanud kasvavat huvi masinõppel põhinevate rakenduste kasutusele võtmiseks. Muuhulgas otsitakse võimalusi oma äriprotsesside efektiivsuse tõstmiseks, kasutades ennustusmudeleid protsesside jooksvaks seireks. Sellised ennustava protsessiseire meetodid võtavad sisendiks sündmuslogi, mis koosneb hulgast lõpetatud äriprotsessi juhtumite sündmusjadadest, ning kasutavad masinõppe algoritme ennustusmudelite treenimiseks. Saadud mudelid teevad ennustusi lõpetamata (antud ajahetkel aktiivsete) protsessijuhtumite jaoks, võttes sisendiks sündmuste jada, mis selle hetkeni on toimunud ning ennustades kas järgmist sündmust antud juhtumis, juhtumi lõppemiseni jäänud aega või instantsi lõpptulemust. Lõpptulemusele orienteeritud ennustava protsessiseire meetodid keskenduvad ennustamisele, kas protsessijuhtum lõppeb soovitud või ebasoovitava lõpptulemusega. Süsteemi kasutaja saab ennustuste alusel otsustada, kas sekkuda antud protsessijuhtumisse või mitte, eesmärgiga ära hoida ebasoovitavat lõpptulemust või leevendada selle negatiivseid tagajärgi. Erinevalt puhtalt ennustavatest süsteemidest annavad korralduslikud protsessiseire meetodid kasutajale ka soovitusi, kas ja kuidas antud juhtumisse sekkuda, eesmärgiga optimeerida mingit kindlat kasulikkusfunktsiooni. Käesolev doktoritöö uurib, kuidas treenida, hinnata ja kasutada ennustusmudeleid äriprotsesside lõpptulemuste ennustava ja korraldusliku seire raames. Doktoritöö pakub välja taksonoomia olemasolevate meetodite klassifitseerimiseks ja võrdleb neid katseliselt. Lisaks pakub töö välja raamistiku tekstiliste andmete kasutamiseks antud ennustusmudelites. Samuti pakume välja ennustuste ajalise stabiilsuse mõiste ning koostame raamistiku korralduslikuks protsessiseireks, mis annab kasutajatele soovitusi, kas protsessi sekkuda või mitte. Katsed näitavad, et väljapakutud lahendused täiendavad olemasolevaid meetodeid ning aitavad kaasa ennustava protsessiseire süsteemide rakendamisele reaalsetes süsteemides.
Recent years have witnessed a growing adoption of machine learning techniques for business improvement across various fields. Among other emerging applications, organizations are exploiting opportunities to improve the performance of their business processes by using predictive models for runtime monitoring. Such predictive process monitoring techniques take an event log (a set of completed business process execution traces) as input and use machine learning techniques to train predictive models. At runtime, these techniques predict either the next event, the remaining time, or the final outcome of an ongoing case, given its incomplete execution trace consisting of the events performed up to the present moment in the given case. In particular, a family of techniques called outcome-oriented predictive process monitoring focuses on predicting whether a case will end with a desired or an undesired outcome. The user of the system can use the predictions to decide whether or not to intervene, with the purpose of preventing an undesired outcome or mitigating its negative effects. Prescriptive process monitoring systems go beyond purely predictive ones, by not only generating predictions but also advising the user if and how to intervene in a running case in order to optimize a given utility function. This thesis addresses the question of how to train, evaluate, and use predictive models for predictive and prescriptive monitoring of business process outcomes. The thesis proposes a taxonomy and performs a comparative experimental evaluation of existing techniques in the field. Moreover, we propose a framework for incorporating textual data to predictive monitoring systems. We introduce the notion of temporal stability to evaluate these systems and propose a prescriptive process monitoring framework for advising users if and how to act upon the predictions. The results suggest that the proposed solutions complement the existing techniques and can be useful for practitioners in implementing predictive process monitoring systems in real life.
Recent years have witnessed a growing adoption of machine learning techniques for business improvement across various fields. Among other emerging applications, organizations are exploiting opportunities to improve the performance of their business processes by using predictive models for runtime monitoring. Such predictive process monitoring techniques take an event log (a set of completed business process execution traces) as input and use machine learning techniques to train predictive models. At runtime, these techniques predict either the next event, the remaining time, or the final outcome of an ongoing case, given its incomplete execution trace consisting of the events performed up to the present moment in the given case. In particular, a family of techniques called outcome-oriented predictive process monitoring focuses on predicting whether a case will end with a desired or an undesired outcome. The user of the system can use the predictions to decide whether or not to intervene, with the purpose of preventing an undesired outcome or mitigating its negative effects. Prescriptive process monitoring systems go beyond purely predictive ones, by not only generating predictions but also advising the user if and how to intervene in a running case in order to optimize a given utility function. This thesis addresses the question of how to train, evaluate, and use predictive models for predictive and prescriptive monitoring of business process outcomes. The thesis proposes a taxonomy and performs a comparative experimental evaluation of existing techniques in the field. Moreover, we propose a framework for incorporating textual data to predictive monitoring systems. We introduce the notion of temporal stability to evaluate these systems and propose a prescriptive process monitoring framework for advising users if and how to act upon the predictions. The results suggest that the proposed solutions complement the existing techniques and can be useful for practitioners in implementing predictive process monitoring systems in real life.
Description
Keywords
business processes, process management, business process modeling