Neo4j Tokyo Meetup – Graph-AI to combat fraud
An amazing 2 hours event, both in Japanese and English languages, divided into three main sessions.
Alberto De Lazzari, Chief Scientist at LARUS, Kanji Uchino, Senior Manager at Fujitsu Labs of America and Sofia Conton, Internalization Program Assistant at LARUS were the protagonists of the first one in which they showed how graph AI can be harnessed to combat fraud in Fintech and Insurtech Sectors.
Starting from LARUS and Fujitsu strong partnership, the main focus was of course on their innovative joint solution, GALILEO XAI, an insight graph data-platform based on eXplainable AI and powered by Fujitsu Deep Tensor.
The solution combines graph-rule-based with graph-supervised-learning coupled with explainability to address fraud prevention.
By exploiting the connectedness of data and extracting new indicators based on the structure of the graph, the solution enabled the anti-fraud team to focus only on relevant groups of subjects or entities, reducing the set of false positives. Furthermore these indicators are seamlessly used by Deep Tensor to constantly improve the results.
If you missed the talk or if you would like to rewatch it, we uploaded the video on YouTube or here below.
Don’t be afraid of the language: the solution demo is entirely in english!
Hope you enjoy it and it can be useful for companies working in the same sector or finding themselves in a similar situation, with similar needs.