网上如何购买目标商品

同一款商品可能会有不同的价格,不同的品质哦,怎么能找到最好的那个呢?     

基于CNN-LSTM的用户购买行为预测模型

利用电商平台上的购物历史数据对用户购买行为进行预测有助于提升用户体验和营销效果。提出一种基于CNN-LSTM的用户购买行为预测模型。使用\"分段下采样\"对样本数据进行均衡化处理以获得购买用户和未购买用户均衡样本;使用CNN-LSTM组合网络实现用户属性、商品属性及用户行为特征的自动抽取与选择,并以此对用户购买行为进行预测。在阿里巴巴移动电商平台数据集的实验结果表明,基于CNN-LSTM的预测模型F1值比基准模型平均提升了7%～11%,使用\"分段下采样\"样本均衡算法F1值提升了2%左右。     

电子商务环境对消费者购买行为的影响研究

电子商务对于我国的经济乃至全球的经济都产生了巨大的推动作用,这种推动作用不止改变了各个相关产业的发展模式,同时更改变了每一个普通消费者的消费模式,甚至是生活模式,然而,这种电子商务的环境究竟对消费者的购买行为产生了什么样的影响呢？本文试图在电子商务自身的特点和消费者的心理两方面上进行探究,寻求影响因素,从而更好的掌握电子商务对消费者的影响。     

深度森林在用户购买预测中的应用

针对电商大数据时代用户未来购买行为预测,在京东平台真实数据集上,提出时间滑动窗口技术和窗口权重递减设置,从五方面构建整体用户行为特征,综合考虑深度学习的表征学习能力和集成学习的训练效率,引入多层异源集成算法,将随机森林、XGBoost等多种算法进行组合,搭建基于深度森林模型的用户购买行为预测算法框架,实现准确高效的用户购买预测结果。算法训练时间为68 s,预测准确率达89.3%,相对于集成学习算法和深度神经网络模型取得了更好的效果。     

基于主题模型的微博转发行为预测

在全部微博内容中,由用户转发而产生的信息占有非常大的比例。同时,内容的转发也是微博中信息传播的主要途径。因此,用户的转发行为有着重要的研究价值,可应用于社交营销、微博检索、热点事件预测等领域中。该文中,我们通过分析所收集的大量真实的新浪微博数据,发现影响用户转发行为的一些因素: 微博作者、用户兴趣以及微博热度。基于这些发现,该文提出了一种新颖的基于LDA模型的方法,综合利用以上3个特征预测用户转发行为。为了对该方法进行评价,我们利用收集的大量的微博数据及对应的社交网络结构模拟真实用户环境。实验表明,该方法的性能优于目前最好的方法,F值比其他基线方法高出35%—45%。     

消费者行为分析的推荐算法研究

随着互联网技术的不断进步,电子商务得到了快速的发展,通过网络购物平台消费已经逐渐成为一种主要消费渠道。在互联网大发展的背景下,庞大的数据量带来便利的同时又为消费者的消费选择造成了困扰。如何从这些数量庞大的商品信息中快速准确地挖掘出消费者所感兴趣的商品成为当前电子商务领域研究的一大热点。随着人工智能技术的不断进步和突破,电子商务企业对消费者的消费倾向及消费能力等作出预测,以实现精准的商品推荐。为进一步了解国内外对消费者行为预测及精准推荐算法的研究,笔者特查阅相关的文献资料,对文献资料进行了分析总结,撰写文献综述,旨在为消费者行为算法的研究提供理论指导。     

用户在线购买预测：一种基于用户操作序列和选择模型的方法

电商网站的兴起与用户在线购物习惯的形成,带来了海量的在线消费行为数据.如何从这些行为数据(如点击数据)中建模用户对相似产品的比较和选择过程,进而准确预测用户的兴趣偏好和购买行为,对于提高产品的购买转化率具有重要意义.针对这一问题,提出了基于用户行为序列数据和选择模型的在线购买预测解决方案.具体而言,1)使用行为序列效用函数估计用户在购买周期(session)中的最佳替代商品,然后对购买商品和最佳替代商品建立基于潜在因子的选择模型(latent factor based choice model, LF-CM),从而得到用户的购买偏好,实现对用户购买行为的预测.更进一步,为了充分地利用用户在每个购买周期的所有选择和比较信息,提高预测精度;2)提出了一种可以作用于购买周期内所有商品的排序学习模型(latent factor and sequence based choice model, LFS-CM),它通过融合潜在因子和行为序列的效用函数,提高了购买预测的精度;3)使用大规模真实数据集在分布式环境下进行了实验,并与参照算法进行了对比,证实了所提出的2个方法在用户在线购买预测上的有效性.     

基于自适应群组重排的长尾推荐模型

针对传统推荐算法过度关注推荐的精度而导致的长尾问题,即热门项目拥有过高的推荐量的同时非热门项目长时间不被关注,提出一种基于欧氏距离构建二维加权相似度并融入自适应群组重排的多目标优化推荐模型（MDOM）——自适应群组重排的推荐模型（AGRM）。首先,利用欧氏距离构建二维加权相似度度量,根据个体历史行为记录动态设定替换比例,并利用融入群组的多目标优化算法解决长尾推荐问题;其次,设计两个简明的目标函数,并同时考虑流行度和长尾关注度,以降低目标函数的复杂性;然后,基于二维加权相似度度量,选择用户子集作为“最佳推荐用户组”,并计算帕累托最优解。在MovieLens 1M和Yahoo数据集上的实验结果表明,AGRM的覆盖率表现最优,与基于物品相似的协同过滤（ItemCF）算法相比,分别平均提升了4.11、25.38个百分点;与用于Top-N推荐的具有浅并行路径的深度变分自动编码器（VASP）模型相比,分别平均提升了8.38、33.19个百分点。在Yahoo数据集上,AGRM的推荐的平均流行度最低,表明AGRM能够推荐更多长尾项目。     

基于Prolog语言的商品推荐知识库模型

针对电子商务个性化推荐问题的特点,引入知识工程的树状表示法,将商品推荐中的三要素转化成描述树进行表达,建立基于Prolog语言的个性化推荐知识库模型。该模型可以根据顾客浏览商品先后次序求解,并与数据库动态地交互数据,实现在线购物的个性化营销。该模型相对独立,通过数据库接口共享电子商务系统数据,能够适应不同结构的电子商务系统。     

ShoppingCat： relocating products from the Web in online shopping

People today increasingly prefer online over conventional shopping. Online shopping possesses numerous advantages and benefits, such as convenience, lower prices, variety, lack of obligation and discreet purchases. However, selecting from among a huge number of products is a challenge for customers. Customers may spend days or even months viewing relevant products on different web sites, occasionally re-locating previously viewed products for comparison, until a final purchase is made. With the large volume of historically viewed products, it is not an easy job for human users to relocate a previously visited product page using conventional access history lists. Also, the product’s ranking may change, making re-finding it difficult or impossible—even using the same keywords in the same online shopping mall. To address this problem, we developed the ShoppingCat system to assist online buyers in re-finding previously viewed product pages via product-related features or previously accessed context features. We evaluated ShoppingCat’s performance in a 2-month user study： its prediction precision was over 70.0%, and the recall rate was 84.7% particularly for the search-then-browse pages.     

一个简单实用型独立购物网站的设计

分析了独立型购物网站的优势,设计并实现了一个简单实用型的独立购物网站系统,该系统不用注册会员,可以直接将商品加入购物车并完成支付。描述了系统前台、后台的基本功能以及数据库的设计,给出了实现购物车的一段源代码。     

Designing social commerce platforms based on consumers’ intentions

Social commerce has been gaining momentum over the last few years as a novel form of e-commerce, creating substantial changes for both businesses and consumers. However, little is known about how consumer behaviour is influenced by characteristics on social commerce platforms. The purpose of this research is to elucidate how user intentions to purchase and to spread word-of-mouth (WOM) are influenced by characteristics present on social commerce platforms. More specifically, we adopt a uses-and-gratifications perspective and examine the influence of socialising, personal recommendation agents, product selection, and information availability. Partial least squares structural equation modelling analysis is performed on a sample of 165 social commerce users. Outcomes of the analysis indicate that socialising and personal recommendation agents positively influence purchase and WOM intentions, while product selection is found to only enhance purchase intentions. Interestingly, our findings reveal that information availability has no significant effect on purchase and WOM intentions. Finally, we find that when purchase intentions are triggered, they will tend increase consumers’ intentions to WOM.     

Understanding online consumers’ purchase intentions: a contribution from social network theory

There is a dynamic and interconnected international setting shaped by the power of the Internet and social media. To gain more consumers, understand their behaviours and needs, and maintain closest relationships with them, businesses should understand how consumers behave in social media and how they vary in their purchase intentions. In the scope of the study, we integrate the social network theory and the theory of planned behaviour to analyse online consumers’ purchase intentions and to investigate their structural positions by analysing their friendships in social networks. We target Twitter users to conduct analysis due to Twitter's popularity in use, market penetration, and opportunity to work with open-source data. This study contributes to a better theoretical understanding of online consumers’ purchase intentions by integrating multiple theoretical perspectives. It expands the literature by considering both online consumers’ friendship network in Twitter and their individual online purchasing intentions. The study also guides e-marketers to design proper strategies for potential and current consumers and target the right sets of people in the social networks.     

试谈基于Web的网上购物系统

对于企业来讲,无论是企业和企业之间(B2B),还是企业和客户之间(B2C)的交易,如果能够实现网上交易将大大提高交易速度节约交易成本.近几年,随着网络数据库技术的进一步发展,使得这一设想逐渐成为现实.     

Behavioral Model of Online Purchasers in E-Commerce Environment

This research studied the behavioral factors of Internet users when making an on-line purchase. A total of 424 responses were collected in a survey, comprising of 179 online responses and 245 mailed responses. The research shows that demographic and most psychological factors, as well as web-savvy features of a virtual storefront appear non influential in determining the probability of an Internet user making a purchase. This is contrary to beliefs held by most e-commerce businesses. The research findings indicate that e-commerce businesses should focus on employing logo assurance services, state-of-the-art security technology, provide an online customer-service center, establish warranties for products and services sold, maintain credit card payment facilities, and lastly, establish a policy for conflict resolution in the event of inaccurate billings. With the research results, a behavioral model of online purchasers is established. The behavioral model could assist e-commerce businesses to focus on the real concerns of consumers. The contribution of the model is to allow e-commerce businesses to streamline their online activities to cater to the major behavioral factors that influence consumers to purchase online. This could greatly increase the ability of e-commerce businesses to offer competitive virtue selling.     

面向社交媒体的分级注意力表情符预测模型

将预测社交媒体表情符的任务作为文本分类问题,将输入文本映射到最有可能的伴随表情符号。首先,通过研究帖子中出现的表情符与标签之间的关系,提出一个基于标签、发帖用户、发帖时间、发帖地点的注意力机制;其次,添加表情符位置特征;最后,探讨注意力机制、分级模型对于表情符预测任务的作用,训练多种模型并比较其预测效果。实验结果表明,模型对于不同使用频率的表情符的预测效果均有显著提升,模型是可行的、高效的。     

电子购物的利弊对策探讨

随着电子商务的发展,网上购物日益盛行,本文主要介绍了网上购物的一些基本知识,分析了网上购物的一些利与弊,并再此基础上介绍了如何保证网上购物的安全性问题.