Both habit persistence and rigidity are basic important characteristic of consumer behavior.Household can receive utility not only from consumption but also from save.The quantity of utility received by household is n...Both habit persistence and rigidity are basic important characteristic of consumer behavior.Household can receive utility not only from consumption but also from save.The quantity of utility received by household is not determined by the level of current consumption and save,but is determined by the growth quantity of both current consumption and save relative to their habit formation levels.According to the characteristics of consumer behavior,this paper constructs a new utility function for household increment utility function,and derives a new consumption function by optimum of consumer behavior.Using the Chinese data,the empirical study shows that the new consumption function is fitted well with consumer behavior.展开更多
为减少构建效用列表的数量和占用的内存,在时间和空间方面提高挖掘性能,提出增量闭合高效用挖掘算法(incremental closed high utility mining,ICHUM),从增量数据集中有效地挖掘闭合高效用项集。此算法提出一个增量分区效用列表结构,该...为减少构建效用列表的数量和占用的内存,在时间和空间方面提高挖掘性能,提出增量闭合高效用挖掘算法(incremental closed high utility mining,ICHUM),从增量数据集中有效地挖掘闭合高效用项集。此算法提出一个增量分区效用列表结构,该结构仅通过一次数据库扫描即可构建和更新列表,更有效地处理增量数据。在构造此列表结构的过程中,算法还应用有效的融合修剪策略,从而减少无效列表的构建数量。在各种数据集上的试验结果表明,与对比算法相比,该算法减少了30%的运行时间和33%的内存消耗,具有一定的可扩展性。展开更多
文摘Both habit persistence and rigidity are basic important characteristic of consumer behavior.Household can receive utility not only from consumption but also from save.The quantity of utility received by household is not determined by the level of current consumption and save,but is determined by the growth quantity of both current consumption and save relative to their habit formation levels.According to the characteristics of consumer behavior,this paper constructs a new utility function for household increment utility function,and derives a new consumption function by optimum of consumer behavior.Using the Chinese data,the empirical study shows that the new consumption function is fitted well with consumer behavior.
文摘为减少构建效用列表的数量和占用的内存,在时间和空间方面提高挖掘性能,提出增量闭合高效用挖掘算法(incremental closed high utility mining,ICHUM),从增量数据集中有效地挖掘闭合高效用项集。此算法提出一个增量分区效用列表结构,该结构仅通过一次数据库扫描即可构建和更新列表,更有效地处理增量数据。在构造此列表结构的过程中,算法还应用有效的融合修剪策略,从而减少无效列表的构建数量。在各种数据集上的试验结果表明,与对比算法相比,该算法减少了30%的运行时间和33%的内存消耗,具有一定的可扩展性。
