Subjects wore T-shirts made from eight fabrics during exercise in a cold environmental condition of 14℃ and 32%RH. Preferences were expressed initially by handling the garments and then again after they had been worn...Subjects wore T-shirts made from eight fabrics during exercise in a cold environmental condition of 14℃ and 32%RH. Preferences were expressed initially by handling the garments and then again after they had been worn. In the trial, subjective responses to 19 sensation descriptors were recorded. The relationships among the subjective preference votes for different types of clothing and psychological sensory factors were studied by means of canonical correlation analysis.Two highly significant canonical correlations were found, which indicated that the subjective overall preference votes after wearing were very closely related to factors describing tactile and " body-fit" sensations. The subjective preference votes from handling were mainly related to the "body-fit" comfort factor. Canonical correlation redundancy analysis showed that the canonical variables for sensory factors were reasonably good predictors of the canonical variables for subjective preferences, but not vice versa.Squared展开更多
We investigate the significance of extreme positive returns in the cross-sectional pricing of cryptocurrencies.Through portfolio-level analyses and weekly cross-sectional regressions on all cryptocurrencies in our sam...We investigate the significance of extreme positive returns in the cross-sectional pricing of cryptocurrencies.Through portfolio-level analyses and weekly cross-sectional regressions on all cryptocurrencies in our sample period,we provide evidence for a positive and statistically significant relationship between the maximum daily return within the previous month(MAX)and the expected returns on cryptocurrencies.In particular,the univariate portfolio analysis shows that weekly average raw and riskadjusted return differences between portfolios of cryptocurrencies with the highest and lowest MAX deciles are 3.03%and 1.99%,respectively.The results are robust with respect to the differences in size,price,momentum,short-term reversal,liquidity,volatility,skewness,and investor sentiment.展开更多
针对顾客产品偏好快速变化对企业分析和预测顾客偏好能力的要求,提出一种面向产品改进的顾客偏好分析与预测方法,首先构建长短期记忆网络模型,预测产品设计迭代期间的情感值和重要度,并计算预测准确度;然后通过基于产品特征情感变化模...针对顾客产品偏好快速变化对企业分析和预测顾客偏好能力的要求,提出一种面向产品改进的顾客偏好分析与预测方法,首先构建长短期记忆网络模型,预测产品设计迭代期间的情感值和重要度,并计算预测准确度;然后通过基于产品特征情感变化模式的产品设计改进模型判断各个特征的变化模式,明确待改进的产品特征及改进优先级;最后以DJI Mini 2无人机的在线评论为例验证了方法的有效性。展开更多
The rapid development of the Intemet makes the social network of information dissemination has undergone tremendous changes. Based on the introduction of social network information dissemination mode, this paper analy...The rapid development of the Intemet makes the social network of information dissemination has undergone tremendous changes. Based on the introduction of social network information dissemination mode, this paper analyzes the influencing factors of information dissemination, establishes the user preference model through CP-nets tool, and combines the AHP principle to mine the user＇s preference order, and obtain the user＇s optimal preference feature Portfolio, and finally collect the user in the microblogging platform in the historical behavior data. the use of NetLogo different users of information dissemination decision to predict.展开更多
Online lodging platforms have become more and more popular around the world.To make a booking in these platforms,a user usually needs to select a city first,then browses among all the prospective options.To improve th...Online lodging platforms have become more and more popular around the world.To make a booking in these platforms,a user usually needs to select a city first,then browses among all the prospective options.To improve the user experience,understanding the zone preferences of a user's booking behavior will be helpful.In this work,we aim to predict the zone preferences of users when booking accommodations for the next travel.We have two main challenges:(1)The previous works about next information of Points Of Interest(Pals)recommendation are mainly focused on users'historical records in the same city,while in practice,the historical records of a user in the same city would be very sparse.(2)Since each city has its own specific geographical entities,it is hard to extract the structured geographical features of accommodation in different cities.Towards the difficulties,we propose DeepPredict,a zone preference prediction system.To tackle the first challenge,DeepPredict involves users'historical records in all the cities and uses a deep learning based method to process them.For the second challenge,DeepPredict uses HERE places API to get the information of pals nearby,and processes the information with a unified way to get it.Also,the description of each accommodation might include some useful information,thus we use Sent2Vec,a sentence embedding algorithm,to get the embedding of accommodation description.Using a real-world dataset collected from Airbnb,DeepPredict can predict the zone preferences of users'next bookings with a remarkable performance.DeepPredict outperforms the state-of-the-art algorithms by 60%in macro Fl-score.展开更多
文摘Subjects wore T-shirts made from eight fabrics during exercise in a cold environmental condition of 14℃ and 32%RH. Preferences were expressed initially by handling the garments and then again after they had been worn. In the trial, subjective responses to 19 sensation descriptors were recorded. The relationships among the subjective preference votes for different types of clothing and psychological sensory factors were studied by means of canonical correlation analysis.Two highly significant canonical correlations were found, which indicated that the subjective overall preference votes after wearing were very closely related to factors describing tactile and " body-fit" sensations. The subjective preference votes from handling were mainly related to the "body-fit" comfort factor. Canonical correlation redundancy analysis showed that the canonical variables for sensory factors were reasonably good predictors of the canonical variables for subjective preferences, but not vice versa.Squared
文摘We investigate the significance of extreme positive returns in the cross-sectional pricing of cryptocurrencies.Through portfolio-level analyses and weekly cross-sectional regressions on all cryptocurrencies in our sample period,we provide evidence for a positive and statistically significant relationship between the maximum daily return within the previous month(MAX)and the expected returns on cryptocurrencies.In particular,the univariate portfolio analysis shows that weekly average raw and riskadjusted return differences between portfolios of cryptocurrencies with the highest and lowest MAX deciles are 3.03%and 1.99%,respectively.The results are robust with respect to the differences in size,price,momentum,short-term reversal,liquidity,volatility,skewness,and investor sentiment.
文摘针对顾客产品偏好快速变化对企业分析和预测顾客偏好能力的要求,提出一种面向产品改进的顾客偏好分析与预测方法,首先构建长短期记忆网络模型,预测产品设计迭代期间的情感值和重要度,并计算预测准确度;然后通过基于产品特征情感变化模式的产品设计改进模型判断各个特征的变化模式,明确待改进的产品特征及改进优先级;最后以DJI Mini 2无人机的在线评论为例验证了方法的有效性。
文摘The rapid development of the Intemet makes the social network of information dissemination has undergone tremendous changes. Based on the introduction of social network information dissemination mode, this paper analyzes the influencing factors of information dissemination, establishes the user preference model through CP-nets tool, and combines the AHP principle to mine the user＇s preference order, and obtain the user＇s optimal preference feature Portfolio, and finally collect the user in the microblogging platform in the historical behavior data. the use of NetLogo different users of information dissemination decision to predict.
基金This work was sponsored by the National Natural Science Foundation of China(Nos.71731004,62072115,61602122,and 61971145)Shanghai Pujiang Program(No.2020PJD005)+1 种基金the Research Grants Council of Hong Kong(No.16214817)the 5GEAR Project and FIT Project from the Academy of Finland.
文摘Online lodging platforms have become more and more popular around the world.To make a booking in these platforms,a user usually needs to select a city first,then browses among all the prospective options.To improve the user experience,understanding the zone preferences of a user's booking behavior will be helpful.In this work,we aim to predict the zone preferences of users when booking accommodations for the next travel.We have two main challenges:(1)The previous works about next information of Points Of Interest(Pals)recommendation are mainly focused on users'historical records in the same city,while in practice,the historical records of a user in the same city would be very sparse.(2)Since each city has its own specific geographical entities,it is hard to extract the structured geographical features of accommodation in different cities.Towards the difficulties,we propose DeepPredict,a zone preference prediction system.To tackle the first challenge,DeepPredict involves users'historical records in all the cities and uses a deep learning based method to process them.For the second challenge,DeepPredict uses HERE places API to get the information of pals nearby,and processes the information with a unified way to get it.Also,the description of each accommodation might include some useful information,thus we use Sent2Vec,a sentence embedding algorithm,to get the embedding of accommodation description.Using a real-world dataset collected from Airbnb,DeepPredict can predict the zone preferences of users'next bookings with a remarkable performance.DeepPredict outperforms the state-of-the-art algorithms by 60%in macro Fl-score.
