Sandra Mitrović

Sandra Mitrović is a postdoctoral researcher at IDSIA (Dalle Molle Institute for Artificial Intelligence) since November 2019. She has a background in Applied Mathematics and Computer Science (University of Montenegro). She did Masters in Data Mining and Knowledge Management at Université Pierre et Marie Curie, Paris 6 and her PhD at KU Leuven. Her research interests encompass natural language processing, representation learning, (social) network analysis and machine learning in general.

• ResearchGate
• LinkedIn
• Google scholar
• ORCID: 0000−0002−5697−5865

• Mitrović, S., & De Weerdt, J. (2020). Churn Modeling with Probalistic Meta Paths-based Representation Learning. INFORMATION PROCESSING & MANAGEMENT, 57(2), 1-12. 10.1016/j.ipm.2019.06.001
• Mitrović, S., Baesens, B., Lemahieu, W., & De Weerdt, J. (2019). tcc2vec: RFM-Informed Representation Learning on Call Graphs for Churn Prediction. INFORMATION SCIENCES, 1-16. 10.1016/j.ins.2019.02.044
• Van Belle, R., Mitrović, S., & De Weerdt, J. (2019). Graph Representation Learning for Fraud Prediction: A Nearest Neighbour Approach. In Graph Representation Learning Workshop, NeurIPS, 2019, https://grlearning.github.io/papers/. Vancouver, Canada: ACM.
• Van Belle, R., Mitrović, S., & De Weerdt, J. (2019). Representation Learning in Graphs for Credit Card Fraud Detection. In ECML PKDD 2019 Workshops on Mining Data for Financial Applications (pp.32-46), Würzburg, Germany: Springer, Cham.
• Mitrović, S., Lecoutere, L., & De Weerdt, J. (2019). A Comparison of Methods for Link Sign Prediction with Signed Network Embeddings. In SNAA@2019 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM). Vancouver, Canada: ACM.
• Coppens, L., De Venter, J., Mitrović, S., & De Weerdt, J. (2019). A comparative study of community detection techniques for large evolving graphs.. In LEG@ECML PKDD: The third International Workshop on Advances in Managing and Mining Large Evolving Graphs collocated with ECML-PKDD (pp.368-384). Würzburg, Germany: Springer, Cham.
• Mitrović, S., & De Weerdt, J. (2019). Probabilistic Random Walks for Churn Prediction using Representation Learning.. In Proceedings of the 14th International Workshop on Mining and Learning with Graphs (MLG), in conjunction with KDD 2018.. London, UK.
• Mitrović, S., & De Weerdt, J. (2019). Dyn2Vec: Exploiting dynamic behaviour using difference networks-based node embeddings for classification.. In Proceedings of the International Conference on Data Science (pp. 194-200). Las Vegas, USA: CSREA Press.
• Mitrović, S., & De Weerdt, J. (2019). Churn Prediction using representation learning with guided random walks.. In Joint International Workshop on Social Influence Analysis and Mining Actionable Insights from Social Networks, SocInf+MAISoN. Stockholm, Sweden: SocInf+MAISon.
• Mitrović, S., Baesens, B., Lemahieu, W., & De Weerdt, J. (2018). On the operational efficiency of different feature types for telco churn prediction. European Journal of Operational Research, 267(3), 1141-1155.
• De Winter, S., Decuypere, T., Mitrović, S., Baesens, B., & De Weerdt, J. (2018). Combining Temporal Aspects of Dynamic Networks with Node2Vec for a more Efficient Dynamic Link Prediction. In U. Brandes, C. Reddy, & A. Tagarelli (Eds.), 2018 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM) (pp. 1234-1241). Barcelona, SPAIN: IEEE.
• Singh, G., & Mitrović, S. (2018). Benefits of Using Symmetric Loss in Recommender Systems. In G. Pasi, B. Piwowarski, L. Azzopardi, & A. Hanbury (Eds.), ADVANCES IN INFORMATION RETRIEVAL (ECIR 2018) Vol. 10772 (pp. 345-356). Grenoble, FRANCE: SPRINGER INTERNATIONAL PUBLISHING AG. 10.1007/978-3-319-76941-7_26
• Sesar, B., Hernitschek, N., Mitrović, S., Ivezic, Z., Rix, H. -W., Cohen, J. G., . . . Waters, C. (2017). Machine-learned Identification of RR Lyrae Stars from Sparse, Multi-band Data: The PS1 Sample. ASTRONOMICAL JOURNAL, 153(5), 16 pages. 10.3847/1538-3881/aa661b
• Mitrović, S., Singh, G., Baesens, B., Lemahieu, W., & De Weerdt, J. (2017). Scalable rfm-enriched representation learning for churn prediction. In Proceedings of the fourth IEEE International Conference on Data Science and Advanced Analytics (DSAA2017) (pp. 79-88). Tokyo (Japan): IEEE.
• Mitrović, S., Baesens, B., Lemahieu, W., & De Weerdt, J. (2017). Churn prediction using dynamic rfm-augmented node2vec. In Proceedings of the Third international workshop on Dynamics in and of Networks, ECML-PKDD 2017 (pp. 122). Skopje (Macedonia): Springer.
• Mitrović, S., & Mueller, H. (2015). Summarizing Citation Contexts of Scientific Publications. In J. Mothe, J. Savoy, J. Kamps, K. PinelSauvagnat, G. J. F. Jones, E. SanJuan, . . . N. Ferro (Eds.), EXPERIMENTAL IR MEETS MULTILINGUALITY, MULTIMODALITY, AND INTERACTION Vol. 9283 (pp. 154-165). Univ Toulouse, Inst Rech Informatique Toulouse UMR 5505 CNRS, Toulouse, FRANCE: SPRINGER-VERLAG BERLIN. 10.1007/978-3-319-24027-5_13

E-Mail: sandra @ idsia.ch

NLP group page