Deep Anomaly Detection
Mehrdad Mamaghani, Principal Data Scientist at Swedbank
Davit Bzhalava, Principal Data Scientist at Swedbank
Anomaly detection has numerous applications in a wide variety of fields. In banking, with ever growing heterogeneity and complexity, it is difficult to discover deviating cases using traditional investigation techniques and pre-defined scenario searches. In this talk we’ll have a walk-through on how Swedbank’s deep learning models run on a state-of-the-art platform can help to detect unseen anomalies and deviations utilizing a large spectrum of features.
Mehrdad Mamaghani and Davit Bzhalava hold PhD degrees in applied mathematical statistics and bioinformatics, respectively. Previously, they have worked within biological research, pharmaceutical and communication industries. At Swedbank, along with rest of the Analytics & AI group, the speakers and their colleagues conduct extensive work and research to better leverage the data within the bank as well as creating frameworks for more efficient and customer-oriented banking processes using deep learning techniques and advanced hardware platforms.
Streaming at King
Anis Nasir, King
King is one of the major mobile gaming companies in the world with numerous mobile games running in production, e.g., candy crush, bubble witch, farm heroes and many others. These games produce billions of events on daily basis, which require to be processed in real-time with latencies within seconds. At King, we have developed an in-house streaming platform called RBEA (rule-based event aggregator), which allows scientists and engineers across King to write streaming application and extract information from the enormous amount of data. The talk will cover various aspects on running streaming platform in production environment at King.
Anis Nasir is a backend engineer at King, working for the streaming platform team for more than a year. Prior to work, he finished his PhD at the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology. His supervisors were Sarunas Girdzijauskas and Seif Haridi.
17:45 Doors Open
18:10 - 18:40: Deep Anomaly Detection
18:40 - 19:10: Pizza and Drinks
19:10 - 19:40: Streaming at King
19:40 - 20:00: Networking