Method and system for generating a prediction network

Computer-implemented method for creating a network from a number of nodes and edges, where each node is assigned data from at least one data source, the data of a data source being changeable, the data assigned to a node describing single forecasts from a prediction market, the method comprising;

• (a) structuring the data according to a predefined taxonomy;
• (b) performing a pattern recognition within first data, the first data being assigned to a first node, whereby the pattern recognition determines and analyzes at least a first sequence of patterns of changes in the first data;
• (c) performing a pattern recognition within second data, the second data being assigned to a second node, whereby the pattern recognition determines and analyzes at least a second sequence of patterns of changes in the second data;
• (d) comparing the first sequence of patterns with the second sequence of patterns and deriving a correlation between the first sequence of patterns and the second sequence of patterns from the comparison result, wherein the correlation defines the dependency between the first node and the second node;
• (e) storing the sequence of patterns and the dependency in a pattern database, whereby the dependency forms an edge between the first node and the second node
• (f) creating a chain between the first node and a third node, where there is no dependent defined between the first node and the third node according to steps (b) through (e), wherein the first node in the network is reachable via a path from the third node, the path comprising a number of dependencies, and wherein the chain between the first node and third node is derived from the number of dependencies;
• and
• (g) storing the chain between the first node and the third node in the pattern database, the chain creating an edge between the first node and the third node.