Abstract: In the area of Association Rule Mining (ARM) the most major algorithms is Apriori algorithm. In the existing Apriori algorithm minimum support and confidence are determined subjectively or through trial and error method, so the algorithm lacks the objectiveness and efficiency. To improve the efficiency of association rules, Particle Swarm Optimization (PSO) algorithm is projected which gives feasible threshold values for minimum support and confidence. In the PSO algorithm, initially it looks for the optimum fitness value of each particle and then finds their corresponding support and confidence as minimum threshold values. The difficulty of PSO algorithm is that it guesses that the items have the same implication without taking into account of their weight/attributes within a transaction or within the whole item space. To overcome this drawback, this study proposes a Weighted Quantum Particle Swarm Optimization algorithm (WQPSO) with weighted mean best position according to fitness values of the particles. WQPSO algorithm provides faster local convergence, fallout in better balance between the global and local searching of the algorithm, so it generates good performance. The proposed WQPSO algorithm is experienced with several benchmark functions and compared with standard PSO. The experimental result shows the supremacy of WQPSO and it is verified by applying the FoodMart2000 database of Microsoft SQL Server 2000. Likewise, in clustering, there are many unsupervised clustering algorithms have been developed one such algorithm is K-Means which is simple and straightforward. The main drawback of the K-Means algorithm is that the result is sensitive to the selection of the initial cluster centroids and may converge to the local optima. This is solved by PSO as it performs globalized search and produces clusters with high intra class similarity.