Nowadays, spatial simulation on land use patterns is one of the key contents of LUCC. Modeling is an important tool for simulating land use patterns due to its ability to integrate measurements of changes in land cove...Nowadays, spatial simulation on land use patterns is one of the key contents of LUCC. Modeling is an important tool for simulating land use patterns due to its ability to integrate measurements of changes in land cover and the associated drivers. The conventional regression model can only analyze the correlation between land use types and driving factors but cannot depict the spatial autocorrelation characteristics. Land uses in Yongding County, which is located in the typical karst mountain areas in northwestern Hunan province, were investigated by means of modeling the spatial autocorrelation of land use types with the purpose of deriving better spatial land use patterns on the basis of terrain characteristics and infrastructural conditions. Through incorporating components describing the spatial autocorrelation into a conventional logistic model, we constructed a regression model （Autologistic model）, and used this model to simulate and analyze the spatial land use patterns in Yongding County. According to the comparison with the conventional logistic model without considering the spatial autocorrelation, this model showed better goodness and higher accuracy of fitting. The distribution of arable land, wood land, built-up land and unused land yielded areas under the ROC curves （AUC） was improved to 0.893, 0.940, 0.907 and 0.863 respectively with the autologistic model. It is argued that the improved model based on autologistic method was reasonable to a certain extent. Meanwhile, these analysis results could provide valuable information for modeling future land use change scenarios with actual conditions of local and regional land use, and the probability maps of land use types obtained from this study could also support government decision-making on land use management for Yongding County and other similar areas.展开更多
为了核算百度外卖客户给企业带来的价值,对百度外卖客户进行价值分析,提出一种改进的最近消费时间、消费频率、消费金额(recency frequency monetary,RFM)模型。该模型由平均订单交易时间间隔、客户一定时期内的交易次数、平均单次订单...为了核算百度外卖客户给企业带来的价值,对百度外卖客户进行价值分析,提出一种改进的最近消费时间、消费频率、消费金额(recency frequency monetary,RFM)模型。该模型由平均订单交易时间间隔、客户一定时期内的交易次数、平均单次订单交易金额、客户贡献时间4个指标构成,运用离差标准化方法对4个指标进行规范化处理,采用主成分分析法计算4个指标的权重,4个指标与指标对应权重的乘积之和为客户的价值,采用K-Means聚类算法将客户分为价值由高到低的客户群。对2017年百度外卖企业某商家为期3个月的4 815名客户的订单交易数据进行聚类,结果表明,4 815名客户可以分为重要保持型客户、忠诚型客户、发展型客户、一般客户、低价值客户5类客户群体。改进后RFM模型可用于百度外卖客户价值分析。展开更多
基金National High Technology Research and Development Program of China, No.2008AA12Z106 National Natural Science Foundation of China, No.40801166 No.40771198
文摘Nowadays, spatial simulation on land use patterns is one of the key contents of LUCC. Modeling is an important tool for simulating land use patterns due to its ability to integrate measurements of changes in land cover and the associated drivers. The conventional regression model can only analyze the correlation between land use types and driving factors but cannot depict the spatial autocorrelation characteristics. Land uses in Yongding County, which is located in the typical karst mountain areas in northwestern Hunan province, were investigated by means of modeling the spatial autocorrelation of land use types with the purpose of deriving better spatial land use patterns on the basis of terrain characteristics and infrastructural conditions. Through incorporating components describing the spatial autocorrelation into a conventional logistic model, we constructed a regression model （Autologistic model）, and used this model to simulate and analyze the spatial land use patterns in Yongding County. According to the comparison with the conventional logistic model without considering the spatial autocorrelation, this model showed better goodness and higher accuracy of fitting. The distribution of arable land, wood land, built-up land and unused land yielded areas under the ROC curves （AUC） was improved to 0.893, 0.940, 0.907 and 0.863 respectively with the autologistic model. It is argued that the improved model based on autologistic method was reasonable to a certain extent. Meanwhile, these analysis results could provide valuable information for modeling future land use change scenarios with actual conditions of local and regional land use, and the probability maps of land use types obtained from this study could also support government decision-making on land use management for Yongding County and other similar areas.
文摘为了核算百度外卖客户给企业带来的价值,对百度外卖客户进行价值分析,提出一种改进的最近消费时间、消费频率、消费金额(recency frequency monetary,RFM)模型。该模型由平均订单交易时间间隔、客户一定时期内的交易次数、平均单次订单交易金额、客户贡献时间4个指标构成,运用离差标准化方法对4个指标进行规范化处理,采用主成分分析法计算4个指标的权重,4个指标与指标对应权重的乘积之和为客户的价值,采用K-Means聚类算法将客户分为价值由高到低的客户群。对2017年百度外卖企业某商家为期3个月的4 815名客户的订单交易数据进行聚类,结果表明,4 815名客户可以分为重要保持型客户、忠诚型客户、发展型客户、一般客户、低价值客户5类客户群体。改进后RFM模型可用于百度外卖客户价值分析。
