双向数据挖掘的反馈预测分析  

Feedback prediction analysis of two-way data mining

作　　者：高利娟[1] 刘云[1] 赵玲[1] 

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《郑州轻工业学院学报（自然科学版）》2011年第6期80-82,共3页Journal of Zhengzhou University of Light Industry:Natural Science

基　　金：国家自然科学基金项目(10502050)

摘　　要：针对常规的数据挖掘预测模型只进行单一预测且未对预测的准确度进行分析等问题,提出了一种将关联模型和基于最小二乘法的回归分析模型相结合的反馈预测模型,并使用最小均方算法对预测进行误差分析.仿真结果表明该模型对中长期预测具有较高的精确度.Aiming at the problem that data mining prediction model can only make simplex forecast and not respond to the accuracy of forecast analysis,in order to forecast future trends,a feedback predictive model was put forward based on combined correlation model and LMS regression model,and minimum mean square algorithm was used to verify accuracy of the model.The simulation results showed that this model has high accuracy in prediction for mid and long-term.

关 键 词：数据挖掘 关联规则 最小二乘法 反馈预测 最小均方算法 

分 类 号：TP311.132.4[自动化与计算机技术—计算机软件与理论]