Data Mining in Macroeconomic Data Sets

National Economic Input-Output (EIO) data describes the monetary transactions among economic sectors. The monetary transactions among these sectors form a weighted bi-directional network from a supply sector to a demand sector and the weight is equivalent to the transaction value between them. In this research, we study the properties of this network and identify patterns of inter-sector dependence evolution by investigating the historical EIO data over the years 1947-1982. Here we make the following contributions: The first is the discovery that economic transactions (the distribution of the weight) are highly skewed, but follow the double Pareto-lognormal distribution (dPlN). The second contribution is the design of a new method, " Multiple Steps of Pattern REcognition in skewed DAta " (M-SPREAD) which identifies patterns and clusters despite the skewness of the data set. We applied our methods on the EIO data and we found interesting and explainable patterns, such as correlations among sectors, various evolution patterns within different transaction scales, outlier sectors and outlier time-stamps. The US Economic Input-Output (EIO) accounts [11] show how industries provide input to, and use output from, other industries to produce Gross Domestic Product (GDP). These accounts provide detailed information on the flows of the goods and services of industries in US dollars, such as the purchase of coal from the coal mining sector by the power generation sector. Graphically, these sectors form a weighted bi-directional network through the economic transactions between them. Individual sectors become the vertices of the network; the edges are generated by the economic transaction relationships from the supply sector to the demand sector. The weight of the edges is measured by the dollar amount of monetary transactions between them. Figure 1 shows an example of part of the economy network composed by three economic sectors and the amount of transactions between each pair of them. Learning the web properties of the economy network, including the web structure, the distribution of the size of transactions as well as the evolution of the network can benefit the understanding of the formation and movement of the interconnections among these sectors and is therefore helpful for the prediction of the change of the economic system in the future. Monetary connections and commodity supply demand transactions determine the interdependence among economic sectors. The existence of supply-demand connections makes the dysfunction of one economic sector jeopardize for the normal operation of the other sector. The disruption of any …