Refine
Document Type
- Bachelor Thesis (3) (remove)
Keywords
- BPM (1)
- Business Process Modeling (1)
- Empfehlungssystem (1)
- Probabilistic finite automata (1)
- Recommender System (1)
Regarding the rising amount of legal regulations, businesses should get the opportunity to use software to fulfill their Compliance Management with the usage of compliance pattern. These patterns are used to represent substantive and structural parts of the processes. This means companies can increase their efficiency and react to new regulations quickly to avoid possible violation which can lead to monetary losses or legal consequences. In the literature are many approaches that deal with compliance pattern but currently there does not exist any list with necessary compliance pattern that companies should face at (Delfmann and Hübers, 2015). The following bachelor thesis classifies 80 research contributions regarding their different approaches of compliance pattern. For that a systematic literature review was executed. As a result, the author developed a graphical classification context that provides an overview of connections between different compliance approaches. Furthermore, an appendix with 32 compliance patterns of the analyzed papers was developed that contains real-world patterns with the classification of the previous sections.
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.
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.