多类关联规则生成算法

Multi-class association rule generation algorithm

针对传统关联规则算法产生的规则关联性弱、种类少的缺点,结合Spearman秩相关系数,提出了一种多类关联算法。该算法在传统算法产生的强规则基础上,利用Spearman秩相关方法计算出规则中产品间的同步异步等相关性。将其作为兴趣度阈值,算法可同时产生同步正规则、异步正规则、同步负规则和异步负规则四类关联规则,且规则间联系紧密。实验结果表明了算法的有效性和优越性。

The association rules generated by traditional algorithms have the shortcomings of few classes and low correlation. Based on the analysis of these shortcomings, and combined with Spearman rank correlation coefficient, a new multi-class association rule algorithm was proposed. Based on the strong association rules generated by traditional algorithms, the new algorithm used Spearman rank correlation to calculate the synchronous and asynchronous correlation coefficient. Setting the correlation coefficient as the interest threshold, the new algorithm can generate synchronous positive rules, contrary positive rules, synchronous negative rules and contrary negative rules. Experiment has been carried out to illustrate the effectiveness and superiority of the algorithm.