Bachelor Thesis
Refine
Year of publication
- 2019 (3) (remove)
Document Type
- Bachelor Thesis (3) (remove)
Has Fulltext
- yes (3) (remove)
Keywords
- BPM (1)
- Business Process Modeling (1)
- Empfehlungssystem (1)
- Probabilistic finite automata (1)
- Recommender System (1)
Institute
- Institut für Wirtschafts- und Verwaltungsinformatik (3) (remove)
The main goal of this paper is to ascertain, if neural networks (especially LSTM) are helpful in predicting processes by making predictions as accurately as possible.
TensorFlow is the used framework in Python to build recurrent neural networks. Two networks are built, whereby one is used for training and the other one for prediction.
Used datasets contain several processes with several events each. With those processes, the network ist trained and afterwards, the parameters are saved. The network for prediction uses these parameters to make predictions.
The neural network is able to make clear predictions about subsequent events. Even branches can be predicted.
When developed further, integration in other programs is possible. It is recommended to use unique names for the events or to rename them.
Social Network of Business Objects (SoNBO) is a concept for aggregating information distributed in he-terogeneous system landscapes and making it available via a single user interface. The central idea is to understand company information as a network (graph). There is already a SoNBO-Explorer which integrates the information of a customer relationship management system (CRM system). The challenge in configuring such an application is to identify the corporate network and thus find out how the stored data is linked within the company. A tool that can visualize the corporate network is helpful for this. In this thesis a selfdeveloped tool (SoNBO-Graph-App) is presented as a prototype, which realizes this visualization. With this application the configuration of the network in the SoNBO Explorer consisting of the merged data can be supported by carrying out that configuration on a graphical level. The prototype is connected to two different databases of a Customer Relationship Management (CRM) system and allows the aggregation of these data so that it is displayed as a graph in an overview. This gives the user a better insight and understanding of the relationship between the different data. This work is part of the longterm research project SoNBO, whose goal is a concept for the integration of information from different business application systems.
The goal of this thesis is to create a recommender system (RS) for business processes, based on the existing ProM plugin RegPFA. To accomplish this task, firstly an interface must be created that sets up and expands a database receiving probabilistic finite automata (PFA) created by RegPFA in tsml format as input. Secondly, a Java program must be designed that uses said database to recommend the process elements that are most likely to follow a given sequence of process elements.