Hans Viehmann is working for ORACLE Corporation as director of product management for the spatial and graph technologies.
He holds a degree in Physics from Hamburg University and started his career in Research before joining ORACLE over twenty-five years ago. After various positions in Presales and Business Development, he joined the Product Management Team in 2011. He is leading a global team of product managers responsible for Oracleâ€™s geospatial products and the graph technologies in the Oracle Database. With his team, he is looking after strategic projects and partnerships, marketing activities, and internal awareness around the Spatial and Graph technologies worldwide. He works closely with various Oracle User Groups and helped establish Spatial and Graph Special Interest Groups in several countries. He is a regular speaker at conferences and user group events and serves on the advisory board of InGeoForum, Germany.
During Contech2022,Hans Viehmann presents Finding suspicious money movements with Graph Analysis and Machine Learning and How far is the nearest pub? Let’s see what the database says.
|Finding suspicious money movements with Graph Analysis – Abstract:|
Graph analysis and machine learning provide different approaches to anomaly detection. This talk will explain how to perform graph analysis and graph pattern matching on financial transactions. Weâ€™ll show how these techniques enhance the accuracy of predictions resulting from machine learning.
Both graph analysis and machine learning are effective techniques to detect anomalies and outliers in datasets. The former is particularly useful when relationships between entities play a role, in other words, when the data represents a network of connected things. Networks of bank accounts connected by financial transactions are one obvious example. For this reason, modern fraud prevention applications perform graph analytics and pattern matching queries on this kind of data. In addition to this approach, increasingly, they are combining graph analysis with machine learning to yield even more accurate results.
This presentation will show how financial service providers search for suspicious patterns in networks of money transfers. We will look at how to prepare relational data for graph analysis and how a machine learning platform can consume the linked data without losing the characteristics of the graph. Finally, we will explain why graph analysis and machine learning yield different results on the same data and discuss how data scientists can combine these techniques.
|How far is the nearest pub? Let’s see what the database says. – Abstract:|
In the past, working with location data in the Oracle Database required a certain amount of expertise. With the release of Spatial Studio in 2019, this has changed. Loading geospatial data, enriching it, creating cartographic maps, or developing analytic workflows has since become very easy even for the non-expert. In this talk, we want to look into how Spatial Studio can help developers and data engineers. We will demonstrate a typical workflow, starting with how to prepare data by converting addresses of bars and restaurants to geographic coordinates. As a next step, we will combine the output with data from various other sources for location-based analysis, render the results on a map in different ways, and then publish them for consumption by other applications. While we will briefly describe the architecture of the underlying platform and explain the database features enabling this kind of analysis, this presentation focuses on the practical demonstration of the tool.