Sirvi Autor "Shoush, Mahmoud, juhendaja" järgi

Nüüd näidatakse 1 - 3 3

Activity-Oriented Causal Process Mining: An End-to-End Approach Utilizing Ylearn
(Tartu Ülikool, 2023) Baltramaitis, Lukas; Milani, Fredrik, juhendaja; Shoush, Mahmoud, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
In recent decades, companies have explored data-driven methods and tools to improve their business processes. More recently, prescriptive business process analysis became popular among data analysts and researchers. There are many studies on the use of prescriptive algorithms for the optimization of a variety of different business processes. Prescriptive algorithms given the historical and/or real-time data try to discover and recommend the best actions to improve the future outcome, e.g. what existing actions in the advertisement process need to be changed to increase the sales. One of the prescriptive methods approaches is Causal Process Mining which uses event logs received from the company’s information systems and then analyses them with Causal Inference algorithms to discover and estimate these possible changes (treatments) that would affect the final outcome. However, all event logs can differ by the variables that are logged and the models may become dependent on the data structure. This means that each event log requires separate variables investigation and modeling that would match the event log data structure. Consequently, performing these activities takes time and resources. A more generic and automated approach could be better applicable in different business cases and give useful results without excessive analysis or model building. For this reason, in this study, we investigate the possibility to use only case ID, activity, and timestamp variables of the event log for the causal inference algorithms. We propose the experimentation software artifact that includes data preparation and integrates the existing Ylearn causal inference tool. The approach is evaluated using five real-world event logs. Evaluation results show that causal relationships can be detected between activities of the event log and estimated treatment effects are comparable with other approaches.
Back-end of Kairos: A Prescriptive Process Monitoring Tool
(Tartu Ülikool, 2023) Qu, Zhaosi; Milani, Fredrik, juhendaja; Shoush, Mahmoud, juhendaja; Kubrak, Kateryna, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Prescriptive process monitoring is an approach that aims to predict potential failures and provide recommendations to optimize business processes. It seeks to improve efficiency and productivity by aiding enterprises in making informed decisions during process execution. For example, it can be applied to optimize a company’s supply chain management by predicting delays and suggesting actions based on historical data. The primary problem that this thesis address is the absence of a comprehensive tool capable of analyzing data from different sources and offering various types of prescriptive recommendations. Consequently, the objective of this study is to propose and implement a software solution that enables the integration of diverse algorithms and plugins in a seamless manner. The proposed approach includes back-end software that provides APIs to implement prescriptive process monitoring features. Users can upload event logs to the tool and receive various prescriptions for ongoing cases, encompassing predictions of the next activities, scoring the likelihood of adverse outcomes, providing treatment effects, and allocating resources based on treatment gains. Moreover, the modular design enhances adaptability and flexibility across various business domains. To evaluate the effectiveness of the proposed solution, a combination of requirements fulfillment evaluation and performance evaluation is conducted using datasets from the Business Process Intelligence Challenge (BPIC). As a result, this thesis contributes to the field by providing a prescriptive process monitoring tool that can provide multiple types of prescriptive recommendations.
Predicting Next Best Action(s) To Improve Sales Metrics For Pipedrive Customers
(Tartu Ülikool, 2023) Darekar, Amey Chandrakant; Shoush, Mahmoud, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Ennustava protsessi jälgimise (PPM) tehnikad kasutavad ajalooliste sündmuste logiandmete kogu potentsiaali, rakendades andmete kaevandamise ja masinõppe meetodeid, et prognoosida protsessi käitumist tulevikus, näiteks ennustada või soovitada järgmist parimat tegevust (või tegevust). Kaasaegsed tehnikad järgmise parima tegevuse soovitamiseks, eriti need, mis kasutavad Deep Neural Networks’i (DNNs), on saavutanud peaaegu täiusliku täpsuse ärikeskkondade tulevase protsessikäitumise ennustamisel. Vaatamata sellele, kuna need tehnikad ei võta arvesse tulemuslikkuse põhinäitajaid (KPI), on näitajad, mida ettevõtted kasutavad protsessi tulemuslikkuse mõõtmiseks, muutes need tehnikad piiratud nende võimega parandada äriprotsesse reaalsetes rakendustes. Protsessisimulatsiooni on varem kasutatud KPIde kaasamiseks, et optimeerida äritehingute protsessivoogu, kuid see meetod on piiratud, kui puuduvad lõplikud tegevuse tulemused. Sellistel juhtudel annavad katsed kasutada protsessi simulatsiooni koos otsuste toetamisega meetmete voogude kontrollimiseks sageli ebasoodsaid tulemusi. Pakume välja lähenemisviisi, mis on inspireeritud äriprotsesside optimeerimisest, mis põhineb tegevuse järjestuste tõenäolisel jaotusel, et ennustada järgmist parimat tegevust. Püüame seda tehnikat rakendada, võttes arvesse KPI-sid, mis optimeerivad müügitehingute edukust, kasutades Pipedrive CRM-ist saadud reaalmaailma sündmuste logisid. Samuti viisime läbi eksperimente heuristiliste otsingustrateegiatega, et mõõta nende kasulikkust, kui need on seotud meie pakutud strateegiaga. Me võrdleme meie pakutud raamistiku jõudlust traditsioonilise kontrollivoolu simulatsioonil põhineva tehnikaga.