Efficient Mining of Association Rules in Oscillatory-based Data

Association rules are one of the most researched areas of data mining. Finding frequent patternsis an important step in association rules mining which is very time consuming and costly. In thispaper, an effective method for mining association rules in the data with the oscillatory value (up,down) is presented, such as the stock price variation in stock exchange, which, just a fewnumbers of the counts of itemsets are searched from the database, and the counts of the rest ofitemsets are computed using the relationships that exist between these types of data. Also, thestrategy of pruning is used to decrease the searching space and increase the rate of the miningprocess. Thus, there is no need to investigate the entire frequent patterns from the database.This takes less time to find frequent patterns. By executing the MR-Miner (an acronym for “MathRules-Miner”) algorithm, its performance on the real stock data is analyzed and shown. Ourexperiments show that the MR-Miner algorithm can find association rules very efficiently in thedata based on Oscillatory value type.