Schedule a Meeting

Anomaly Detection in Business Processes: Next4biz EIAD Model

As the Next4biz R&D team, we presented our study, Edge Information Assisted Decoder for Business Process Anomaly Detection, at the 8th International Artificial Intelligence and Data Processing Symposium (IDAP’24) to enhance anomaly detection in business processes.

Loading...

Anomaly detection as a subject focuses on the identification of data point which significantly deviate from what is the norm or the standard of the dataset. This gives anomaly detection a wide range of applications where the detection of irregularities is often times of crucial importance such as Business Process Management (BPM). 

In this study we present a novel type of decoder referred to as ”Edge Information Assisted Decoder” (EIAD), working on graph data to incorporate edge indexes and attributes into the decoding to achieve improved anomaly detection. We tested a total of 8 encoder-decoder combinations to comparatively evaluate them and prove the effectiveness of the proposed method. 

The proposed method and the best encoder-decoder combination, the graph attention network (GAT) encoder and the edge-conditioned convolution (ECC) decoder yielded an increase of 0.31 in F1-score from 0.32 to 0.63 when compared to the baseline multi-layer perceptron (MLP) decoder model, both with the optimal optimizer. The empirical results show that the proposed approach has a potential to improve graph based anomaly detection.

For more details, you can review our study:

Schedule a Meeting
We use cookies in accordance with legal regulations to improve our services and your experience on our site. By clicking "I Understand" button, you accept our cookie policy. You can go to settings to edit your cookie preferences.
Our Cookie Policy and Your Privacy

Necessary Cookies

Always enabled
Necessary cookies enable the basic functions of the website to ensure that it operates as intended. The website cannot function properly without these cookies.
Our Cookie Policy Our Privacy Policy

Functionality and Analytics Cookies

Functionality and analytics cookies aim to provide a more functional usage experience in future visits based on users' past use of the website. These cookies enable websites to offer personalized services such as language and region preferences by processing statistics and activity data.
Our Cookie Policy Our Privacy Policy

Targeting and Performance Cookies

Targeting and performance cookies are cookies that anonymously collect visitors' usage information and preferences related to the website, thereby enhancing the website's performance and improving user experiences based on visitor preferences.
Our Cookie Policy Our Privacy Policy

Advertising Cookies

Advertising cookies are third-party cookies used on websites to track visitors' behaviors. The purpose of these cookies is to display advertisements that are relevant and appealing to the visitors' needs.
Our Cookie Policy Our Privacy Policy