地球信息科学学报 ›› 2016, Vol. 18 ›› Issue (11): 1494-1499.doi: 10.3724/SP.J.1047.2016.01494

• 特约稿件 • 上一篇    下一篇

基于主成分Logistic模型的商圈吸引力因子分析

姚丽贞1,3(), 乐阳1,2,**()   

  1. 1. 深圳大学土木工程学院, 深圳 518060
    2. 空间信息智能感知与服务深圳市重点实验室, 深圳 518060
    3. 百度国际科技(深圳)有限公司, 深圳 518057
  • 收稿日期:2016-07-21 修回日期:2016-09-30 出版日期:2016-11-20 发布日期:2016-11-20
  • 通讯作者: 乐阳 E-mail:yaolizhen715@foxmail.com;yueyang@szu.edu.cn
  • 作者简介:

    作者简介:姚丽贞(1991-),女,硕士生,研究方向为数据分析与挖掘。E-mail: yaolizhen715@foxmail.com

  • 基金资助:
    深圳市科技计划项目(JCYJ20130329144141856);国家自然科学基金项目(41671387)

Factor Analysis of Shopping Center Attractiveness Based on Principal Component Logistic Model

YAO Lizhen1,3(), YUE Yang1,2,*()   

  1. 1. College of Civil Engineering, Shenzhen University, Shenzhen 518060, China
    2. Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen 518060, China
    3. Baidu (Shezhen) International Co. Ltd, Shenzhen 518057, China
  • Received:2016-07-21 Revised:2016-09-30 Online:2016-11-20 Published:2016-11-20
  • Contact: YUE Yang E-mail:yaolizhen715@foxmail.com;yueyang@szu.edu.cn

摘要:

重力模型是地理学的经典模型之一,常用于解释和预测人口、货物、交通、财富等的移动现象。其中Huff模型被广泛用于预测商圈规模,但目前多数研究以商场的面积作为吸引力的度量指标,不能准确反映商场真实的吸引力,造成模型预测的误差。本文针对Huff模型常使用规模表达商圈吸引力的不足,在对购物中心吸引力进行总结的基础上,选择了深圳市5个具有代表性的大型购物中心(或商圈)进行问卷调查。利用因子分析方法识别出6个影响购物中心吸引力的因子:可达性因子、环境因子、私家车出行因子、多功能因子、商品因子和个人特征因子。基于主成分Logistic模型,分析购物中心吸引力的显著影响因素及权重。最后,通过对比不同参照系下购物中心的显著性因素,对商圈吸引力因子进行可靠性检验。本文的分析方法及结果可为Huff模型等的精细化建模提供基础。

关键词: 吸引力因子, 重力模型, Huff模型, 主成分Logistic模型, 商圈分析

Abstract:

As one of the most classical geography models, Huff model has been widely used in explaining and predicting the movement of human, goods, transport, and currency. In determining trade area for shopping centers, the size of the shopping center is the most commonly used parameter to reflect its attractiveness. However, the attractiveness of a shopping center is usually determined by many other factors, such as price, services, accessibility and environment. Therefore, using size as the measurement of shopping center attractiveness could cause misleading results. To obtain the actual attractiveness factors that should be used in Huff model, this study conducted a questionnaire on five representative shopping malls in one of the largest city in Shenzhen, China, and identified six factors using factor analysis. Then, we used principal component Logistic model to obtain their level of significances and corresponding weights. The results of this study could be helpful to parameter selection of Huff model and thus improve the accuracy of model prediction.

Key words: attractiveness factors, gravity model, Huff model, principal component logistic model, trade area analysis