%0 Conference Paper %1 ls_leimeister %A Karst, Fabian Sven %A Li, Mahei Manhai %A Leimeister, Jan Marco %B International Conference on Design Science Research in Information Systems and Technology (DESRIST) %C Pretoria, South Africa %D 2023 %K data_sharing dempub ecosystem fraud_detection generative_adversarial_networks itegpub platform pub_jml pub_mli synthetic_data training_data %T Synthesizing Training Data with Generative Adversarial Networks: Towards the Design of a Data-Sharing Ecosystem Platform for Fraud Detection %X Financial fraud has a severe impact on the general population. While financial institutions have technological capabilities for fraud detection using intelligent AI systems, the delay until they have collected a sufficient size of fraudulent data to train their fraud detection models creates a costly vulnerability. One major challenge for quickly training data lies in the inability to share fraud detection training data with other financial institutions, due to data and privacy regulations. Thus, we create the concept for a data-sharing ecosystem platform that addresses data anonymity concerns by creating synthesized training data based on each institution’s fraud detection training data sets. We rely on the advantages of generative adversarial networks (GAN) to quickly construct a shared dataset for all ecosystem members. Applying design science research, this paper derives design knowledge based on financial fraud detection literature, data sharing between financial institutions, GANs and modular systems theory for the design of a plat-form architecture for data-sharing ecosystems.

@inproceedings{ls_leimeister, abstract = {Financial fraud has a severe impact on the general population. While financial institutions have technological capabilities for fraud detection using intelligent AI systems, the delay until they have collected a sufficient size of fraudulent data to train their fraud detection models creates a costly vulnerability. One major challenge for quickly training data lies in the inability to share fraud detection training data with other financial institutions, due to data and privacy regulations. Thus, we create the concept for a data-sharing ecosystem platform that addresses data anonymity concerns by creating synthesized training data based on each institution’s fraud detection training data sets. We rely on the advantages of generative adversarial networks (GAN) to quickly construct a shared dataset for all ecosystem members. Applying design science research, this paper derives design knowledge based on financial fraud detection literature, data sharing between financial institutions, GANs and modular systems theory for the design of a plat-form architecture for data-sharing ecosystems.}, added-at = {2023-03-24T11:28:28.000+0100}, address = {Pretoria, South Africa}, author = {Karst, Fabian Sven and Li, Mahei Manhai and Leimeister, Jan Marco}, biburl = {https://www.bibsonomy.org/bibtex/22101d290e1fcb2cf6e70fcb92ab4c3b5/ls_leimeister}, booktitle = {International Conference on Design Science Research in Information Systems and Technology (DESRIST)}, eventdate = {31 May - 02 Jun 2023}, eventtitle = {International Conference on Design Science Research in Information Systems and Technology (DESRIST)}, interhash = {87364c9e99abf85f66eff5d13b527e45}, intrahash = {2101d290e1fcb2cf6e70fcb92ab4c3b5}, keywords = {data_sharing dempub ecosystem fraud_detection generative_adversarial_networks itegpub platform pub_jml pub_mli synthetic_data training_data}, language = {English}, timestamp = {2023-06-07T12:47:20.000+0200}, title = {Synthesizing Training Data with Generative Adversarial Networks: Towards the Design of a Data-Sharing Ecosystem Platform for Fraud Detection}, venue = {Pretoria, South Africa}, year = 2023 }