An Application of the Data Mining Methods with Decision Rule

Abstract

Abstract —Rankings for output of Chinese main agricultural com-modity in the world for 1978, 1980, 1990, 2000, 2006, 2007 and 2008have been released in United Nations FAO Database. Unfortunately,where the ranking of output of Chinese cotton lint in the world for2008 was missed. This paper uses sequential data mining methodswith decision rules filling this gap. This new data mining methodwill be help to give a further improvement for United Nations FAODatabase. Keywords —Ranking, output of the main agricultural commodity,gross domestic product, decision table, information system; datamining, decision rule I. I NTRODUCTION Recently, Food and Agriculture Organization of the UnitedNations has released rankings for output of Chinese mainagricultural commodity in the world, i.e., the following datatable was given ([10]), where u 1 ,u 2 ,u 3 ,u 4 ,u 5 ,u 6 ,u 7 denote1978,1980,1990,2000,2006,2007,2008.T ABLE I:I NCOMPLETE D ATA T ABLE Item u 1 u 2 u 3 u 4 u 5 u 6 u 7 Cereals 2 1 1 1 1 1 1Meat 3 3 1 1 1 1 1Cotton Lint 3 2 1 1 1 1Soybeans 3 3 3 4 4 4 4Groundnuts in Shell 2 2 2 1 1 1 1Sugar Cane 7 9 4 3 3 3 3Tea 2 2 2 1 1 1 1Fruit 9 10 4 1 1 1 1The above data in Table 1 also appear in [1]. In Table1, numbers in the first row denote years and others denoterankings. Unfortunately, Table 1 is an incomplete Data table,which does not give the ranking for output of Chinese cottonlint in the world for 2008. Thus, the following question arisenaturally.