Al-Based Privacy-Preserving Big Data Sharing for Market Research (ANITA-ANonymous bIg daTA)


Type Research Project

Funding Bodies
  • Austrian Research Promotion Agency

Duration Oct. 1, 2019 - Nov. 30, 2021

http://www.anonymousbigdata.net/
  • Institute for Marketing and Customer Analytics IN (Details)

Tags

Press 'enter' for creating the tag
  • Drozd, Olha (Former researcher)
  • Eigenschink, Peter (Details)
  • Reutterer, Thomas (Details) Project Head
  • Valendin, Jan (Former researcher)
  • Vamosi, Stefan (Details)
 

Abstract (German)

Offener Datenaustausch hat das Potential den wissenschaftlichen Fortschritt zu beschleunigen und positive Wohlfahrtseffekte zu generieren. Ziel dieses Forschungsprojektes ist es generative neuronale Netzwerkarchitekturen für sequenzielle, personenbezogene Daten zu trainieren, um anschließend systematisch zu validieren, inwiefern die Verwendung solcher synthetischer, datenschutzkonformer Daten für die Marketingforschung Dritter nutzbar sind.


Partners

  • Bundesanstalt "Statistik Österreich" - Austria
  • George Labs GmbH - Austria
  • Mostly Al Solutions MP GmbH - Austria

Publications

Journal article

2022 Vamosi, Stefan, Reutterer, Thomas, Platzer, Michael. 2022. A Deep Recurrent Neural Network Approach to Learn Sequence Similarities for User-Identification. Decision Support Systems (DSS). (Details)
  Valendin, Jan, Reutterer, Thomas, Platzer, Michael, Kalcher, Klaudius. 2022. Customer base analysis with recurrent neural networks. International Journal of Research in Marketing. open access (Details)
2021 Platzer, Michael, Reutterer, Thomas. 2021. Holdout-Based Empirical Assessment of Mixed-Type Synthetic Data. Frontiers in Big Data. 4 1-12. open access (Details)
  Reutterer, Thomas, Platzer, Michael, Schröder, Nadine. 2021. Leveraging purchase regularity for predicting customer behavior the easy way. International Journal of Research in Marketing. 38 (1), 194-215. (Details)

Contribution to conference proceedings

2020 Vamosi, Stefan, Reutterer, Thomas. 2020. A RECURRENT NEURAL NETWORK WITH TRIPLET LOSS APPROACH FOR SIMILARITY MATCHING AND USER RE-IDENTIFICATION. In EMAC 2020 Annual Conference, Hrsg. EMAC, 1-11. Budapest: EMAC. (Details)

Paper presented at an academic conference or symposium

2021 Platzer, Michael, Reutterer, Thomas, Vamosi, Stefan. 2021. AI-based re-identification exposes privacy risk of behavioral data. A case for synthetic data. EMAC 2021 Annual Conference, Madrid (online), Spanien, 25.05.-28.05. (Details)
2020 Vamosi, Stefan, Reutterer, Thomas. 2020. Show me a snippet of your browsing history and I tell you who you are: A recurrent neural net with triplet loss approach for User re-identification. 18th Annual International Conference on Marketing, Athens, Griechenland, 29.06-02.07. (Details)
2019 Vamosi, Stefan, Reutterer, Thomas. 2019. A deep learning approach to quantify sequence similarities of historical customer data. 2019 INFORMS Marketing Science Conference, Rome, Italien, 20.06.-22.06. (Details)
  Vamosi, Stefan, Reutterer, Thomas, Platzer, Michael, Kalcher, Klaudius. 2019. A Deep Learning Approach to Quantify Sequence Similarities of Historical Customer Data. INFORMS Marketing Science Conference 2019, Rom, Italien, 20.06.-22.06. (Details)

Working/discussion paper, preprint

2021 Eigenschink, Peter, Vamosi, Stefan, Vamosi, Ralf, Sun, Chang, Reutterer, Thomas, Kalcher, Klaudius. 2021. Deep Generative Models for Synthetic Data. (Details)
  Platzer, Michael, Reutterer, Thomas. 2021. Holdout-Based Fidelity and Privacy Assessment of Mixed-Type Synthetic Data. (Details)