Association rule mining is the most popular data mining techniques to find association among items in a set by mining necessary patterns in a large database, frequently used in marketing, advertising and inventory control. Typically association rules consider only items enumerated in transactions, referred as positive association rules but not consider negative occurrence of attributes that are also useful in market-basket analysis to identify products that conflict with each other or products that complement each other. Also for mining those positive rules that qualify the user specified threshold criteria, algorithm generates too many candidate itemsets by scanning database multiple times. In order to resolve all the bottleneck of association rule mining algorithm, in this we propose an algorithm SARIC which implements Set Particle Swarm Optimization heuristic technique for generating association rules from a database that also consider negative occurrence of attribute along with positive occurrence. SARIC uses the concept of IR and Correlation Coefficient and there is no need to specify minimum support and confidence, it automatically determines them quickly and objectivel