Thoughts on:

      "Fast Algorithms for Mining Association Rules",
      Rakesh Agrawal,
      Ramakrishnan Srikant
      IBM Almaden Research Center, 1994

      
This paper introduces the Apriori algorithm for mining association
rules. This will most likely be the algorithm we base our's on.

    

      

	count item occurrences
      
      

	determine large 1-itemsets
      
      

	each subsequent pass, k,  involves two steps
	

	  

	    large itemsets Lk-1 found in the previous pass are 
	    used to generate the candidate itemsets Ck using the
	    apriorigen function.
	  
	  

	    the support of the candidates in Ck is counted