宁波大学学报:理工版
寧波大學學報:理工版
저파대학학보:리공판
Journal of Ningbo University(Natural Science and Engineering Edition)
2012年
3期
58-61
,共4页
K_means%密度%RFM扩展模型%游客细分
K_means%密度%RFM擴展模型%遊客細分
K_means%밀도%RFM확전모형%유객세분
K_means%density%extended RFM model%tourists classification
针对传统K_means算法存在的问题,提出一种基于密度的初始中心点选择方法,并利用几何三角形三边关系理论简化了迭代中的计算次数,以缩短大数据集聚类时间.针对旅游电子商务的特点,基于RFM模型设计了一种RFMVCI扩展模型.新算法的有效性和扩展模型的合理性在实验和旅游客户细分实践中获得了验证.
針對傳統K_means算法存在的問題,提齣一種基于密度的初始中心點選擇方法,併利用幾何三角形三邊關繫理論簡化瞭迭代中的計算次數,以縮短大數據集聚類時間.針對旅遊電子商務的特點,基于RFM模型設計瞭一種RFMVCI擴展模型.新算法的有效性和擴展模型的閤理性在實驗和旅遊客戶細分實踐中穫得瞭驗證.
침대전통K_means산법존재적문제,제출일충기우밀도적초시중심점선택방법,병이용궤하삼각형삼변관계이론간화료질대중적계산차수,이축단대수거집취류시간.침대여유전자상무적특점,기우RFM모형설계료일충RFMVCI확전모형.신산법적유효성화확전모형적합이성재실험화여유객호세분실천중획득료험증.
An improved density-based K_means algorithm is presented for the existing problems of traditional K_means clustering algorithm, in which selection of initial center pointer is optimized. Also, the triangular trilateral relation theorem is introduced to reduce calculation complexity. An expanded RMF model (RFMVCI) is presented in applications of tourism electronic business, and the validity of new algorithm and rationality of extended model are validated in practice of tourism customer classification.