dc.contributorGonzález Rojas, Oscar Fernando
dc.contributorDumas, Marlon
dc.contributorMuñoz-Gama, Jorge
dc.contributorVilo, Jaak
dc.contributorNúñez Castro, Haydemar María
dc.contributorPedraza Ferreira, Gabriel Rodrigo
dc.contributorMatulevicius, Raimundas
dc.contributorSánchez Puccini, Mario Eduardo
dc.contributorTICSw
dc.creatorCamargo Chávez, Manuel Alejandro
dc.date.accessioned2022-02-18T20:07:56Z
dc.date.available2022-02-18T20:07:56Z
dc.date.created2022-02-18T20:07:56Z
dc.date.issued2021-11-11
dc.identifierhttp://hdl.handle.net/1992/54943
dc.identifierinstname:Universidad de los Andes
dc.identifierreponame:Repositorio Institucional Séneca
dc.identifierrepourl:https://repositorio.uniandes.edu.co/
dc.description.abstractModern organizations need to constantly adjust their business processes in order to adapt to internal and external changes, such as new competitors, new regulations, changes in customer expectations, or changes in strategic objectives. For example, due to a pandemic, a retailer might experience a 50% increase in their number of online orders while, during the same time, their volume of in-store purchases declines by 30%. To adjust to these changes, the managers may decide to re-deploy employees from the retail stores to the warehouses of the company and the company's online customer service department. To inform their decisions, the managers need to have an accurate estimate of the impact of the above changes on the delivery and customer service response times. A common approach to make such estimates is to use Business Process Simulation (BPS). BPS refers to the use of computers to explore the dynamics of a business process over time. BPS has long proven to be a useful approach to answer what-if questions in the context of business process redesign. At the same time, the predictions made by BPS models are known to be relatively inaccurate due to the way they are usually applied. Traditionally, domain experts create simulation models manually by using manual data gathering techniques (e.g. interviews, observations, and sampling). This approach makes the creation of simulation models time-consuming and error-prone. In real-life, business processes tend to be more complex than what domain experts can capture in a manually designed simulation model. Yet, any omission in the simulation model can significantly affect the accuracy and reliability of a simulation. Other limitations of current BPS approaches arise from fundamental assumptions that business process simulation engines make. For example, business process simulation engines assume that human workers work in a robotic (or factory-line) style- meaning that they conduct their work continuously during working hours, without any distractions, without multitasking, and without fatigue. In other words, current business process simulation approaches are not able to capture and reproduce the complexity of human behavior. In this context, this thesis investigates the following overarching question: How to automatically create accurate business process simulation models based on data extracted from enterprise information systems? Previous research on this question has demonstrated the viability of using a family of techniques for the analysis of business process execution data, known as process mining, to semi-automatically extract BPS models from execution data. Such techniques are fall under the banner of Data-Driven Simulation (DDS). This thesis starts by noting that existing techniques in the field of DDS require manual intervention and fine-tuning to produce accurate simulation models. To address this gap, the thesis presents and evaluates a fully automated technique for DDS capable of discovering and fine-tuning BPS models through process mining techniques. The core idea of the technique is to assess the accuracy of a BPS model automatically using a similarity measure that considers both the ordering of activities and their execution times. On this basis, the proposed technique employs a Bayesian optimization algorithm to maximize the similarity between the behavior generated by the BPS model and the behavior observed in the execution data. The thesis, thus, shows that the proposed DDS technique generates models that accurately reflect the ordering of activities. However, the proposed technique often falls short when it comes to predicting the timing of each activity. This phenomenon is due to the assumptions that BPS techniques make about the behavior of resources in the process. To tackle this shortcoming, the thesis combines DDS techniques based on process mining, with generative modeling techniques based on deep learning. In this respect, the thesis makes two contributions. First, it proposes an approach to learn generative deep learning models that are able to produce timestamped sequences of activities (with associated resources) based on historical execution data. Second, it proposes an approach to combine DDS techniques based on process mining, with generative deep learning modeling techniques. The thesis shows that this hybrid approach to learn BPS models leads to simulations that more closely reflect the observed sequences of activities and their timings compared to a DDS technique based purely on process mining and techniques based purely on deep learning.
dc.description.abstractLas organizaciones modernas necesitan ajustar constantemente sus procesos de negocio para adaptarse a cambios en su entorno interno y externo, tales como, nuevos competidores, nuevas regulaciones, cambios en las expectativas de los clientes o cambios en los objetivos estratégicos. Por ejemplo, debido a una pandemia, un minorista puede experimentar un aumento del 50% en su número de pedidos en línea, mientras que, durante el mismo tiempo, su volumen de compras en la tienda disminuye en un 30%. Para adaptarse a estos cambios, los gerentes pueden decidir reasignar a los empleados de las tiendas minoristas a los almacenes de la empresa y al departamento de atención al cliente en línea de la empresa. Para tomar decisiones informadas, los gerentes necesitan una estimación precisa del impacto de los cambios anteriores en los tiempos de respuesta de entrega y servicio al cliente. Un enfoque común para realizar tales estimaciones es utilizar Simulación de Procesos de Negocio (BPS por sus siglas en inglés). BPS se refiere al uso de computadoras para explorar la dinámica de un proceso comercial a lo largo del tiempo. BPS ha demostrado durante mucho tiempo ser un enfoque útil para responder preguntas hipotéticas en el contexto del rediseño de procesos comerciales. Al mismo tiempo, se sabe que las predicciones efectuadas por los modelos de BPS son relativamente inexactas debido a la forma en que se aplican habitualmente. Tradicionalmente, los expertos en el dominio crean modelos de simulación manualmente empleando técnicas de recopilación de datos manuales (por ejemplo, entrevistas, observaciones y muestreo). Este enfoque hace que la creación de modelos de simulación requiera mucho tiempo y sea propensa a errores. En la vida real, los procesos de negocio tienden a ser más complejos de lo que los expertos en el dominio pueden capturar en un modelo de simulación diseñado manualmente. Sin embargo, cualquier omisión en el modelo de simulación puede afectar significativamente la precisión y confiabilidad de una simulación. Otras limitaciones de los enfoques actuales de BPS surgen de supuestos fundamentales que hacen los motores de simulación de procesos de negocio. Por ejemplo, los motores de simulación asumen que los trabajadores humanos trabajan en un estilo robótico (o de línea de fábrica), lo que significa que realizan su trabajo continuamente durante las horas de trabajo, sin distracciones, sin realizar múltiples tareas y sin fatiga. En otras palabras, los enfoques de simulación de procesos comerciales actuales no pueden capturar y reproducir la complejidad del comportamiento humano. En este contexto, esta tesis investiga la siguiente pregunta general: ¿Cómo crear automáticamente modelos precisos de simulación de procesos de negocio basados en datos extraídos de los sistemas de información empresarial? Investigaciones anteriores sobre esta cuestión han demostrado la viabilidad de utilizar una familia de técnicas para el análisis de datos de ejecución de procesos comerciales, conocida como minería de procesos, para extraer semiautomáticamente modelos BPS de los datos de ejecución. Estas técnicas se encuentran bajo el nombre de Simulación Basada en Datos (DDS por sus siglas en inglés). Esta tesis comienza señalando que las técnicas existentes en el campo de DDS requieren una intervención manual y un ajuste fino para producir modelos de simulación precisos. Para abordar esta brecha, la tesis presenta y evalúa una técnica totalmente automatizada para DDS capaz de descubrir y ajustar modelos BPS empleando técnicas de minería de procesos. La idea central de la técnica es evaluar la precisión de un modelo BPS automáticamente mediante una medida de similitud que considera tanto el orden de sus actividades como sus tiempos de ejecución. Sobre esta base, la técnica propuesta utiliza un algoritmo de optimización bayesiano para maximizar la similitud entre el comportamiento generado por el modelo BPS y el comportamiento observado en los datos de ejecución. La tesis muestra que la técnica DDS propuesta genera modelos que reflejan con precisión el orden de las actividades. Sin embargo, dicha técnica a menudo se queda corta cuando se trata de predecir el momento de cada actividad. Este fenómeno se debe a los supuestos que hacen las técnicas de BPS sobre el comportamiento de los recursos en el proceso. Para abordar esta deficiencia, la tesis combina técnicas de DDS basadas en minería de procesos, con modelos generativos de Deep Learning. En este sentido, la tesis hace dos aportes. Primero, propone un enfoque para aprender modelos generativos de Deep Learning que pueden producir secuencias de actividades con marcas de tiempo (y recursos asociados) basadas en datos de ejecución históricos. En segundo lugar, propone un enfoque para combinar técnicas de DDS basadas en minería de procesos, con técnicas de modelado generativo de Deep Learning. La tesis muestra que este enfoque híbrido para aprender modelos BPS conduce a simulaciones que reflejan más de cerca las secuencias de actividades observadas y sus tiempos en comparación con una técnica DDS basada puramente en la minería de procesos o técnicas basadas puramente en Deep Learning.
dc.description.abstractKaasaegsed organisatsioonid peavad oma äriprotsesse pidevalt muutma, et kohaneda erinevate sisemiste ja välimiste muutustega nagu näiteks uued konkurendid, uued regulatsioonid, muutused klientide ootustes või muutused strateegilistes eesmärkides. Näiteks pandeemia oludes võib jaemüüja internetikaubanduse maht suureneda 50%, samas kui kohapeal sooritatud ostude maht langeb näiteks 30%. Sellise muutunud olukorraga kohanemiseks võib jaemüüja otsustada töötajate ümberpaigutamise jaekauplustest ettevõtte ladudesse ja veebipõhise klienditeeninduse osakonda. Seda tüüpi otsuste teadlikuks vastuvõtmiseks on jaemüüjal vaja täpset hinnangut selle kohta, millist mõju antud otsus avaldaks kaupade kohaletoimetamise ja klientide päringutele vastamise aegadele. Tavapärane lähenemine selliste hinnangute andmiseks on kasutada äriprotsesside simuleerimist. Äriprotsesside simuleerimine viitab äriprotsesside ajalise dünaamika arvuti abil uurimisele ja tegemist on kasuliku lähenemisega vastamaks "mis-oleks-kui" tüüpi küsimustele äriprotsesside ümberdisainimise kontekstis. Samas, tulenevalt sellest kuidas äriprotsesside simuleerimist tavaliselt rakendatakse, on selle lähenemisega saadud ennustused teadaolevalt suhteliselt ebatäpsed. Äriprotsesside simuleerimisel kasutatavad simulatsioonimudelid luuakse tavaliselt valdkonna ekspertide poolt käsitsi, kasutades manuaalseid andmekogumismeetodeid (intervjuud, vaatlused, valikulised andmete väljavõtted), mis omakorda muudab simulatsioonimudelite loomise ajamahukaks ja veaaltiks. Reaalsuses on äriprotsesside käitumine sageli oluliselt keerukam sellest, mida valdkonna eksperdid suudaksid käsitsi koostatud simulatsioonimudelites kajastada. Samas iga simulatsioonimudelist välja jäänud detail võib oluliselt mõjutada äriprotsesside simuleerimise täpsust ja usaldusväärsust. Teised olemasolevate äriprotsesside simuleerimise lähenemiste puudujäägid tulenevad äriprotsesside simulatsioonimootorite poolt tehtavatest põhimõttelistest eeldustest. Näiteks eeldus et inimesed töötavad robotitele (või tehase tööliinidele) sarnasel viisil, ehk et tööd tehakse töötundide jooksul järjepidevalt, püsiva tähelepanuga, kõrvalistele töödele aega kulutamata ja väsimatult. Ehk teisisõnu, olemasolevad äriprotsesside simuleerimise lähenemised ei ole võimelised kajastama ja seega ka taaslooma inimkäitumise keerukust. Ülaltoodust lähtuvalt uurib käesolev doktoritöö järgnevat üleüldist küsimust: Kuidas automatiseeritult luua täpseid äriprotsesside simulatsioonimudeleid tuginedes ettevõttete infosüsteemidest kogutud andmetele? Antud küsimusega seonduv varasem teadustöö on näidanud, et äriprotsessi käitlemisandmete analüüsitehnikaid, mida tervikuna nimetatakse protsessikaeveks, on võimalik edukalt kasutada äriprotsesside simulatsioonimudelite pool-automatiseeritult loomiseks ning vastavate tehnikate kohta kasutatakse üldnimetust andmepõhine simuleerimine. Käesolev doktoritöö juhib kõigepealt tähelepanu tõsiasjale, et täpsete simulatsioonimudelite loomine, kasutades olemasolevaid andmepõhise simuleerimise tehnikaid, nõuab käsitsi sekkumist ja peenhäälestamist. Selle puudujäägi lahendamiseks esitatakse ja hinnatakse käesolevas doktoritöös andmepõhise simuleerimise täielikult automatiseeritud lahendus, mis suudab tuvastada ja peenhäälestada simulatsioonimudeleid rakendades protsessikaeve tehnikaid. Lahenduse tuumikidee on automatiseeritult hinnata simulatsioonimudeli täpsust, arvestades nii tegevuste järjekorda kui ka tegevuste kestuseid. Täpsuse hinnangule tuginedes rakendatakse antud lähenemises Bayesi optimeerimisalgoritmi eesmärgiga saavutada maksimaalne sarnasus simulatsioonimudeli poolt genereeritud käitumise ja äriprotsessi käitlemisandmete vahel. Seejärel näitab käesolev doktoritöö, et esitatud andmepõhise simuleerimise tehnika loob simulatsioonimudeleid, mis peegeldavad tegevuste järgnevusi täpselt, aga samas ei suuda sageli täpselt ennustada tegevuste kestust. Antud puudujääk on põhjustatud andmepõhise simuleerimise tehnikates tehtavatest eeldustest seoses ressursside käitumisega äriprotsessides. Antud puudujäägi lahendamiseks kombineeritakse käesolevas doktoritöös protsessikaevel tuginevaid andmepõhise simuleerimise tehnikaid ja generatiivseid süvaõppepõhiseid modelleerimise tehnikaid. Selles osas esitab käesolev doktoritöö kaks teaduslikku panust. Esiteks, lähenemine generatiivsete süvaõppe mudelite loomiseks, mis võimaldavad protsessi ajalooliste käitlemisandmete põhjal genereerida ajatembeldatud sündmuste järgnevusi koos sündmustele vastavate ressurssidega. Teiseks, lähenemine protsessikaevel tuginevate andmepõhise simuleerimise tehnikate ja generatiivsete süvaõppepõhiste modelleerimise tehnikate kombineerimiseks. Käesolev doktoritöö näitab, et sellise hübriidlähenemisega loodud simulatsioonimudelid võimaldavad luua simulatsioone, mis peegeldavad protsessi käitlemisandmetes sisalduvaid sündmuste järgnevusi ja kestuseid täpsemalt kui ainult andmepõhisele simulatsioonile tuginevad tehnikad ja täpsemalt kui ainult süvaõppele tuginevad tehnikad.
dc.languageeng
dc.publisherUniversidad de los Andes
dc.publisherDoctorado en Ingeniería
dc.publisherFacultad de Ingeniería
dc.publisherDepartamento de Ingeniería de Sistemas y Computación
dc.relationWil M. P. van der Aalst. Business Process Simulation Survival Guide. In: Handbook on Business Process Management 1: Introduction, Methods, and Information Systems. Ed. by Jan vom Brocke and Michael Rosemann. Springer, 2015, pp. 337-370.
dc.relationWil M. P. van der Aalst. Process Modeling and Analysis. In: Process Mining: Data Science in Action. Springer, 2016, pp. 5588.
dc.relationWil M. P. van der Aalst and et al. Process Mining Manifesto. In: Proceedings of BPM Workshops 2012. LNBIP. Springer, 2012, pp. 169194.
dc.relationWil M. P. van der Aalst, Ton Weijters, and Laura Maruster. Workflow mining: Discovering process models from event logs. In: IEEE Transactions on Knowledge and Data Engineering 16.9 (2004), pp. 11281142.
dc.relationMadis Abel. Lightning Fast Business Process Simulator. MA thesis. University of Tartu, 2011.
dc.relationA. Adriansyah, B. van Dongen, and W. van der Aalst. Conformance checking using cost-based fitness analysis. In: Proceedings of EDOC 2011. IEEE, 2011, pp. 5564.
dc.relationArya Adriansyah et al. Alignment based precision checking. In: Proceedings of BPM Workshops 2012. LNBIP. Springer, 2013, pp. 137149.
dc.relationAbel Armas-Cervantes et al. Local Concurrency Detection in Business Process Event Logs. In: ACM Transactions on Internet Technology 19.1 (2019), pp. 123.
dc.relationAdriano Augusto et al. Automated Discovery of Process Models from Event Logs: Review and Benchmark. In: IEEE Transactions on Knowledge and Data Engineering 31.4 (2018), pp. 686705.
dc.relationAdriano Augusto et al. Split miner: automated discovery of accurate and simple business process models from event logs. In: Knowledge and Information Systems 59.2 (2019), pp. 251284.
dc.relationEkaterina Bazhenova, Susanne Buelow, and Mathias Weske. Discovering Decision Models from Event Logs. In: Proceedings of BIS 2016. LNBIP. Springer, 2016, pp. 237251.
dc.relationJames Bergstra et al. Algorithms for Hyper-parameter Optimization. In: Proceedings of NIPS 2011. Curran Associates Inc., 2011, pp. 25462554.
dc.relationDominic Breuker et al. Comprehensible Predictive Models for Business Processes. In: MIS Quarterly 40.4 (2016), pp. 10091034.
dc.relationManuel Camargo, Marlon Dumas, and Oscar González-Rojas. Automated discovery of business process simulation models from event logs. In: Decision Support Systems 134 (2020), p. 113284.
dc.relationManuel Camargo, Marlon Dumas, and Oscar González-Rojas. Discovering generative models from event logs: data-driven simulation vs deep learning. In: PeerJ Computer Science 7 (2021), e577.
dc.relationManuel Camargo, Marlon Dumas, and Oscar González-Rojas. Learning Accurate LSTM Models of Business Processes. In: Proceedings of BPM 2019. Vol. 168. LNCS. Springer, 2019, pp. 286302.
dc.relationManuel Camargo, Marlon Dumas, and Oscar González-Rojas. Simod : A Tool for Automated Discovery of Business Process Simulation Models. In: Proceedings of BPM Dissertation Award, Doctoral Consortium, and Demonstration Track 2019. CEUR, 2019, pp. 139143.
dc.relationJunyoung Chung et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. In: Proceedings of NIPS Workshops 2014. 2014, pp. 19.
dc.relationChiara Di Francescomarino et al. An eye into the future: Leveraging a- priori knowledge in predictive business process monitoring. In: Proceedings of BPM 2017. LNCS. Springer, 2017, pp. 252268.
dc.relationNicola Di Mauro, Annalisa Appice, and Teresa M. A. Basile. Activity Prediction of Business Process Instances with Inception CNN Models. In: Proceedings of AI*IA 2019. LNCS. Springer, 2019, pp. 348361.
dc.relationRemco M. Dijkman, Marlon Dumas, and Chun Ouyang. Semantics and analysis of business process models in BPMN. In: Information and Software Technology 50.12 (2008), pp. 12811294.
dc.relationMarlon Dumas et al. Fundamentals of Business Process Management. Second Edition. Springer, 2018.
dc.relationBedilia EstradaTorres et al. Discovering business process simulation models in the presence of multitasking and availability constraints. In: Data & Knowledge Engineering 134 (2021), p. 101897.
dc.relationJoerg Evermann, Jana Rebecca Rehse, and Peter Fettke. Predicting process behaviour using deep learning. In: Decision Support Systems 100 (2017), pp. 129140.
dc.relationCédric Favre, Dirk Fahland, and Hagen Völzer. The relationship between workflow graphs and free-choice workflow nets. In: Information Systems 47 (2015), pp. 197219.
dc.relationCédric Favre and Hagen Völzer. The Difficulty of Replacing an Inclusive OR-Join. In: Proceedings of BPM 2012. LNCS. Springer, 2012, pp. 156 171.
dc.relationJoão Gama et al. A survey on concept drift adaptation. In: ACM Computing Surveys 46.4 (2014), pp. 137.
dc.relationBartlomiej Gawin and Bartosz Marcinkowski. How Close to Reality is the as-is Business Process Simulation Model In: Organizacija 48.3 (2015), pp. 155176.
dc.relationN. Gilbert and K. Troitzsch. Simulation For The Social Scientist. Open University Press, 2005.
dc.relationIan Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. http://www.deeplearningbook.org. MIT Press, 2016.
dc.relationXing Hao, Guigang Zhang, and Shang Ma. Deep Learning. In: International Journal of Semantic Computing 10.03 (2016), pp. 417439.
dc.relationAlan R. Hevner et al. Design science in information systems research. In: MIS quarterly (2004), pp. 75105.
dc.relationMarkku Hinkka, Teemu Lehto, and Keijo Heljanko. Exploiting event log event attributes in RNN based prediction. In: Proceedings of ADBIS 2019. CCIS. Springer, 2020, pp. 405416.
dc.relationSepp Hochreiter and Jürgen Schmidhuber. Long Short-Term Memory. In: Neural Computation 9.8 (1997), pp. 17351780.
dc.relationMonique Jansen-Vullers and Mariska Netjes. Business process simulationa tool survey. In: Workshop and Tutorial on Practical Use of Coloured Petri Nets and the CPN Tools, Aarhus, Denmark 38 (2006).
dc.relationAbdulrhman Al-Jebrni, Hongming Cai, and Lihong Jiang. Predicting the Next Process Event Using Convolutional Neural Networks. In: Proceedings of PIC 2018. IEEE, 2018, pp. 332338.
dc.relationIvan Khodyrev and Svetlana Popova. Discrete modeling and simulation of business processes using event logs. In: Procedia Computer Science 29 (2014), pp. 322331.
dc.relationBartek Kiepuszewski, Arthur H. M. ter Hofstede, and Wil M. P. van der Aalst. Fundamentals of control flow in workflows. In: Acta Informatica 39.3 (2003), pp. 143209.
dc.relationHarold W. Kuhn. The Hungarian Method for the assignment problem. In: Naval Research Logistics Quarterly 2 (1955), pp. 8397.
dc.relationM. Laguna and J. Marklund. Business Process Modeling, Simulation and Design. CRC Press, 2018.
dc.relationYann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep learning. In: Nature 521.7553 (2015), pp. 436444.
dc.relationYann LeCun et al. Gradient-based learning applied to document recognition. In: Proceedings of the IEEE 86.11 (1998), pp. 22782323.
dc.relationSander J. J. Leemans et al. Stochastic process mining: Earth movers stochastic conformance. In: Information Systems 102 (2021), p. 101724.
dc.relationDafna Levy. Production Analysis with Process Mining Technology. 2014.
dc.relationLi Lin, Lijie Wen, and Jianmin Wang. MM-Pred: A Deep Predictive Model for Multi-attribute Event Sequence. In: Proceedings of SIAM 2019. Society for Industrial and Applied Mathematics, 2019, pp. 118126.
dc.relationOrlenys López-Pintado et al. Silhouetting the Cost-Time Front: Multiobjective Resource Optimization in Business Processes. In: Proceedings of BPM Forum 2021. LNBIP. Springer, 2021, pp. 92108.
dc.relationSanidhya Mangal, Poorva Joshi, and Rahul Modak. LSTM vs. GRU vs. Bidirectional RNN for script generation. 2019. arXiv: 1908.04332. URL: http://arxiv.org/abs/1908.04332.
dc.relationFelix Mannhardt et al. Decision mining revisited Discovering overlapping rules. In: Proceedings of CAiSE 2016. LNCS. Springer, 2016, pp. 377392.
dc.relationNiels Martin, Benoît Depaire, and An Caris. The use of process mining in a business process simulation context: Overview and challenges. In: Proceedings of CIDM Symposium 2014. IEEE, 2014, pp. 381388.
dc.relationNiels Martin, Benoît Depaire, and An Caris. The Use of Process Mining in Business Process Simulation Model Construction. In: Business & Information Systems Engineering 58.1 (2016), pp. 7387.
dc.relationNiels Martin, Benoît Depaire, and An Caris. Using Event Logs to Model Interarrival Times in Business Process Simulation. In: Proceedings of BPM Workshops 2015. LNBIP. Springer, 2015, pp. 255267.
dc.relationNiels Martin, Luise Pufahl, and Felix Mannhardt. Detection of batch activities from event logs. In: Information Systems 95 (2021), p. 101642.
dc.relationNijat Mehdiyev, Joerg Evermann, and Peter Fettke. A Multi-stage Deep Learning Approach for Business Process Event Prediction. In: Proceedings of CBI 2017. IEEE, 2017, pp. 119128.
dc.relationTomas Mikolov et al. Efficient estimation of word representations in vector space. In: Proceedings of ICLR Workshops 2013. 2013, pp. 112.
dc.relationSander J. J. Leemans, Dirk Fahland, and Wil M. P. van der Aalst. Scalable process discovery and conformance checking. In: Software and Systems Modeling 17.2 (2018), pp. 599631.
dc.relationJoos C. A. M. Buijs, Boudewijn F. van Dongen, and Wil M. P. van der Aalst. Quality dimensions in process discovery: The importance of fitness, precision, generalization and simplicity. In: International Journal of Cooperative Information Systems 23.1 (2014), p. 1440001.
dc.relationJorge Munoz-Gama. Conformance Checking and Diagnosis in Process Mining. LNBIP. Springer International Publishing, 2016.
dc.relationJorge Munoz-Gama, Josep Carmona, and Wil M. P. Van Der Aalst. Conformance checking in the large: Partitioning and topology. In: Business Process Management. LNCS. Springer, 2013, pp. 130 145.
dc.relationLaura Muruster and Nick R. T. P. van Beest. Redesigning business processes: a methodology based on simulation and process mining techniques. In: Knowledge and Information Systems 21.3 (2009), pp. 267 297.
dc.relationNicolò Navarin et al. LSTM networks for data-aware remaining time prediction of business process instances. In: Proceedings of SSCI Symposium 2017. IEEE, 2017, pp. 1 7.
dc.relationTimo Nolle, Alexander Seeliger, and Max Mühlhäuser. BINet: Multivariate Business Process Anomaly Detection Using Deep Learning. In: Proceedings of BPM 2018. LNCS. Springer, 2018, pp. 271 287.
dc.relationChun Ouyang et al. Modelling complex resource requirements in Business Process Management Systems. In: Proceedings of ACIS 2010. 2010, pp. 1 11.
dc.relationA. Pnueli. The temporal logic of programs. In: Proceedings of SFCS 1977. IEEE, 1977, pp. 46 57.
dc.relationMirko Polato et al. Time and activity sequence prediction of business process instances. In: Computing 100.9 (2018), pp. 1005 1031.
dc.relationMahsa Pourbafrani, Shuai Jiao, and Wil M. P. van der Aalst. SIMPT: Process Improvement Using Interactive Simulation of Time-Aware Process Trees. In: Proceedings of RCIS 2021. LNBIP. 2021, pp. 588 594.
dc.relationMahsa Pourbafrani, Sebastiaan J. van Zelst, and Wil M. P. van der Aalst. Supporting Automatic System Dynamics Model Generation for Simulation in the Context of Process Mining. In: Proceedings of BIS 2020. LNBIP. 2020, pp. 249 263.
dc.relationLuise Pufahl, Tsun Yin Wong, and Mathias Weske. Design of an Extensible BPMN Process Simulator. In: Proceedings of BPM Workshops 2017. LNBIP. Springer, 2017, pp. 782 795.
dc.relationEfrén Rama-Maneiro, Juan C. Vidal, and Manuel Lama. Deep Learning for Predictive Business Process Monitoring: Review and Benchmark. 2021. arXiv: 2009.13251 [cs.LG]. URL: https://arxiv.org/abs/2009. 13251.
dc.relationDaniel Reißner et al. Scalable alignment of process models and event logs: An approach based on automata and S-components. In: Information Systems 94 (2020), p. 101561.
dc.relationAndreas Rogge-Solti et al. In Log and Model We Trust? A Generalized Conformance Checking Framework. In: Proceedings of BPM 2016. LNCS. Springer, 2016, pp. 179 196.
dc.relationAnne Rozinat, Ronny S. Mans, and Wil. M. P. van der Aalst. Discovering simulation models. In: Information Systems 34.3 (2009), pp. 305 327.
dc.relationAnne Rozinat, Ronny S. Mans, and Wil. M. P. van der Aalst. Mining CPN Models: Discovering Process Models with Data from Event Logs. In: In Workshop and Tutorial on Practical Use of Coloured Petri Nets and the CPN. 2006, pp. 57 76.
dc.relationToma Rusinaite et al. An approach for allocation of shared resources in the rule-based business process simulation. In: Proceedings of CompSysTech 2016. ACM, 2016, pp. 25 32.
dc.relationMohammadreza Fani Sani et al. Conformance Checking Approximation Using Simulation. In: Proceedings of ICPM 2020. IEEE, 2020, pp. 105 112.
dc.relationJürgen Schmidhuber. Deep Learning in neural networks: An overview. In: Neural Networks 61 (2015), pp. 85 117.
dc.relationStefan Schönig et al. Deep learning process prediction with discrete and continuous data features. In: Proceedings of ENASE 2018. SCITEPRESS, 2018, pp. 314 327.
dc.relationRenuka Sindhgatta et al. Exploring Interpretable Predictive Models for Business Processes. In: Proceedings of BPM 2020. LNCS. Springer, 2020, pp. 257 272.
dc.relationMinseok Song and W. M. P. van der Aalst. Towards comprehensive support for organizational mining. In: Decision Support Systems 46.1 (2008), pp. 300 317.
dc.relationSuriadi Suriadi et al. Discovering work prioritisation patterns from event logs. In: Decision Support Systems 100 (2017), pp. 77-92.
dc.relationNiek Tax, Irene Teinemaa, and Sebastiaan J. van Zelst. An interdisciplinary comparison of sequence modeling methods for next-element prediction. In: Software and Systems Modeling 19.6 (2020), pp. 1345 1365.
dc.relationNiek Tax et al. Predictive Business Process Monitoring with LSTM Neural Networks. In: Proceedings of CAiSE 2017. LNCS. Springer, 2017, pp. 477 492.
dc.relationSean J. Taylor and Benjamin Letham. Forecasting at Scale. In: American Statistician 72.1 (2018), pp. 37 45.
dc.relationFarbod Taymouri et al. Predictive Business Process Monitoring via Generative Adversarial Nets: The Case of Next Event Prediction. In: Proceedings of BPM 2020. LNCS. Springer, 2020, pp. 237 256.
dc.relationIrene Teinemaa, Anna Leontjeva, and Karl-Oskar Masing. BPIC 2015: Diagnostics of building permit application process in dutch municipalities. In: BPI Challenge Report. 2015.
dc.relationJulian Theis and Houshang Darabi. Decay Replay Mining to Predict Next Process Events. In: IEEE Access 7 (2019), pp. 119787 119803.
dc.relationAshish Vaswani et al. Attention is All You Need. In: Proceedings of NIPS 2017. Curran Associates Inc., 2017, pp. 5998 6008.
dc.relationNils Witt and Christin Seifert. Understanding the Influence of Hyperparameters on Text Embeddings for Text Classification Tasks. In: Proceedings of TPDL 2017. LNCS. Springer, 2017, pp. 193 204.
dc.relationMoe Thandar Wynn et al. Business process simulation for operational decision support. In: Proceedings of BPM Workshops 2007. LNBIP. Springer, 2008, pp. 66 77.
dc.rightsAl consultar y hacer uso de este recurso, está aceptando las condiciones de uso establecidas por los autores.
dc.rightshttps://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.titleAutomated discovery of business process simulation models from event logs: a hybrid process mining and deep learning approach
dc.typeTrabajo de grado - Doctorado


Este ítem pertenece a la siguiente institución