This paper introduces two fast algorithms for solving the problem of discovering association rules between items in a very large database of sale transactions. AprioriHybrid, a hybrid algorithm which combines the best features of the two proposed algorithm, has an excellent scale-up properties shown in experiments. The algorithms are proposed based on the problem that how to find all sets of items (itemsets) that have support above the minimum support (i.e. the large itemsets). To determine the large itemsets, algorithms make multiple passes over the data (D) to determine which itemsets are large. The first pass is to count support of individual items and the subsequent passes are: 1) use previous pass’s sets to determine new potential large itemsets; 2) count support for candidates by passing over D and removes those above minsup; 3) repeat the above. The Apriori produces candidates only using previously found large itemsets. In this way, any subset of a large itemset must be large and adding an element to an itemset cannot increase the support. On pass k Apriori grows the large itemsets of k-1 size to produce itemsets of size k. The procedure of Apriori is that it begins with all large 1-itemsets and finds large itemsets of increasing size until the end; then it generates candidate itemset via previous pass’s large itemsets via the Apriori-Gen algorithm; in the end it counts the support of each candidate and keeps those above minsup. Apriori-Gen joins the k-1 itemsets that differ by only the last element and ensures ordering.