E-commerce Data Research Articles

The power of platforms and apps-empowering and controlling the consumer

This article discusses the new marketing model of e-commerce platforms in the Internet age. Merchants use e-commerce platforms as marketing methods to make profits. Customers, as Internet users, when they enjoy the benefits brought by e-commerce platforms, algorithms and data are controlling their thought and action. This article is mainly based on the academic foundation of three publications: the "platform capitalism" written by Nick in 2017, 'Appified -Culture in the Age of Apps' written by Jeremy Wade Morris and Sarah Murray in 2018, 'When Platform Capitalism Meets Petty Capitalism in China: Alibaba and an Integrated Approach to Platformization' written by LIN ZHANG in 2020, analyzes how the Chinese e-commerce platform, Taobao, influences the Internet consumers, and compares the Chinese e-commerce platforms and western e-commerce platforms.

Implementation of Distributed Operation and Maintenance of Cross-Border e-Commerce Platform Based on Cloud Native Architecture

The traditional architecture of e-commerce data management needs to adapt to the new and more complex environment, which needs to provide massive data management, compatibility of different types of data, and better user experience. Cloud computing technology is a synthesis of parallel, distributed, and grid computing and is one of the future directions of information technology development. In this paper, we use cloud computing data management technology to study the data management of e-commerce. It is hoped that the current e-commerce data management can be improved with the help of cloud computing technology. This paper starts from analyzing the current e-commerce representatives Taobao.com and Jingdong Mall to find out the data characteristics of these two enterprises, analyze the existing data problems, and find the aspects that can be improved. Using this open-source cloud computing implementation solution, we solve the storage problem of large files and unstructured small files in the e-commerce system.

Basic Product Data in E-Commerce: Specifications and Problems of Data Exchange

Basic Product Data in E-Commerce: Specifications and Problems of Data Exchange

Aspect Based Sentiment Analysis for E-Commerce Shopping Website

Abstract: Sentiment Analysis is that the most ordinarily used approach to research knowledge that is within the form of text and to identify sentiment content from the text. Opinion Mining is another name for sentiment analysis. a good vary of text data is getting generated within the form of suggestions, feedback, tweets, and comments. E-Commerce portals area unit generating tons of data. Every day within the form of customer reviews. Analyzing E-Commerce data can facilitate on-line retailers to grasp customer expectations, offer an improved searching expertise, and to extend sales. Sentiment Analysis can be used to identify positive, negative, and neutral information from the customer reviews. Researchers have developed a lot of techniques in Sentiment Analysis. Keywords: Sentiment analysis, Sentiment classification, Feature selection, Emotion detection, Customer Reviews;

Structural Balance Theory-based E-commerce Recommendation Over Big Rating Data

Recommending appropriate product items to the target user is becoming the key to ensure continuoussuccess of Ecommerce. Today,many E-commerce systems adopt various recommendation techniques, e.g., Collaborative Filtering (abbreviated as CF)-based technique, to realize product item recommendation. Overall,the present CF recommendation can perform verywell, ifthe target user ownssimilar friends(userbased CF), or the product items purchased and preferred by target user own one or more similar product items (itembased CF). While due to the sparsity of big rating data in Ecommerce, similar friends and similar product items may be both absent from the user-product purchase network, which lead to a big challenge to recommend appropriate product items to the target user. Considering the challenge, we put forward a Structural Balance Theory-based Recommendation (i.e., SBT-Rec) approach. In the concrete, (Ⅰ) user-based recommendation: we look for target user’s “enemy” (i.e., the users having opposite preference with target user); afterwards, we determine target user’s “possible friends”, according to “enemy’s enemy is a friend” rule of Structural Balance Theory, and recommend the product items preferred by “possible friends” of target user to the target user. (Ⅱ) likewise, for the product items purchased and preferred by target user, we determine their “possibly similar product items” based on Structural Balance Theory and recommend them to the target user.

Internet business Information The board

Product management is crucial for e-commerce businesses, and it can help you crush the competition if you have the correct e-commerce data management software in place. You are only as successful in the realm of online commerce as the administration of your product data. Data is the new money in the online and digital world. You can outperform your rivals and boost your profitability if you know how to use it to your advantage. Ecommerce data management, to put it simply, is a highly collaborative and organised modern system that assists you in managing, sharing, and accessing vast quantities of essential product data that are highly valuable to your company. By allowing you to respond to market demands more swiftly, effective data management also aids in keeping you competitive. When meeting the needs of your consumers, EDM enables you to work more efficiently and with less time and human mistake [13]. Product Data Management is a structured approach to assist in managing, gaining access to, and disseminating vast amounts of essential product data that is highly beneficial to your company. The product catalog, attributes, product content, and the consumer data gathered are typically included in this information in eCommerce. In this paper , we have studied How to choose a database management system. There are several database management systems available. Each of them has benefits and downsides in its own particular ways. We tried to compare the databases that are frequently used for both small web applications and massive data warehousing systems, even though we haven't even touched on a third of all databases. So, how do for your own software program? Did you choose the best choice? Databases like MySQL might be a logical starting point for local eCommerce businesses that are just getting off the ground and are compatible with OLTP and web-based BI TOOLS. If you want to create a massive eCommerce company that offers a full customer journey, Cassandra is a good option.. You may also attach the Elasticsearch database solution to it to give it a strong search engine as an addition. In relation to Cassandra, it's also a respectable option for data centres and real-time analytics with massive amounts of data. It may be fair to choose NoSQL databases like MongoDB when discussing analytical tools without numerous data layers. It works great for product catalogs as well. MSSQL is also important to note in the context of data warehousing applications, especially for businesses that have several different Microsoft subscriptions. Oracle is a strong option as well for developing OLTP solutions and data warehousing applications. Our list of the finest use cases for Redis will be summarized by IoT applications and microservice architecture that prefer to scale its data hosting. Yes, there are more database systems to take into account. Your business concept and needs will determine everything. Currently, e-commerce websites not only supply massive amounts of data to e-commerce businesses, but also provide insights data using so many analytics techniques [5].

Research on Three-Dimensional Packing Model and Analysis of Spatial Algorithms for Distribution Center

The B2C retail e-commerce logistics center is constantly developing towards the intelligence and unmanned direction. In the automatic packaging, there are problems of low efficiency and low utilization of box volume caused by packing algorithm. The current common spatial analysis algorithm and three-dimensional packing algorithm and so on are analyzed. Based on the above analysis and combined with the order characteristics of retail e-commerce, a three-dimensional packing model of multi-box with multi-commodity is established. Hybrid Genetic Algorithm and MATLAB are used to solve the model and its solution method are verified by a retail e-commerce data.

Analysis on the scale measurement of the Sino-German digital trade and China's strategy

As a new type of trade trend, digital trade has been triggering profound changes in global production chains, supply chains, and value chains. As two major economies, the analysis on the development scale of digital trade between China and Germany is not only conducive to promoting the cooperation of digital trade between the two countries but also conducive to promoting the high-quality development of China's digital trade. Based on the OECD-WTO conceptual framework and indicator system, this article uses the e-commerce data of cross-border goods and the data of digital service trade to measure the scale of "digitally-ordered trade—digitally-delivered trade" between China and Germany. This article also analyzes the development of digital trade between Germany and China, draws on the advantages of Germany's digital trade , and puts forward countermeasures for China's digital trade development based on the development trend of global digital trade.

Impact of Covid-19 Pandemic on Financial Inclusion and Digital Adoption

Digitalization is an inevitable fact due to increasing technology and the environment that challenges the status-quo of the traditional transactional systems. Especially during the Covid-19 pandemic, the adoption rate of eCommerce and digital transactions has increased significantly. In this research paper, we used eCommerce data of Hungary, Austria, Greece, and Sweden and their DESI index for 2017 to 2020 in order to understand the background of events which shows that the covid-19 pandemic had a significant impact on people’s perception of the day-by-day transactions and that the economic development of a country has a profound impact on the financial inclusion metrics and digitalization appetite of their citizens. Our main findings show that curfews during the pandemic significantly influence the volume of eCommerce transactions and DESI Index rankings are substantially linked with real-life matters.

LEGAL PROTECTION OF DATA SECURITY OF E-COMMERCE APPLICATIONS DURING THE COVID-19 PANDEMIC

The rapid progress in the field of information technology has contributed greatly to the development of the world of information and electronic transactions. The security of consumer personal data that enters e-commerce data should be a guarantee given by the company to its consumers. This study aims to find out the legal protection for data/information security of e-commerce application users during a pandemic. This study uses normative legal research with analytical descriptive methods to explain, describe, and correlate legal regulations and theories with the problems that occur. Data analysis was carried out qualitatively. The results of the study indicate that the electronic system operator must ensure the availability of service level agreements, the availability of information security agreements for the information technology services used; and security of information and means of internal communication held. Then, the operator of the electronic system must ensure that each component and the integration of the entire electronic system operates properly. Especially in the era of the covid-19 pandemic, it is appropriate that the regulation of personal data protection can be immediately upgraded to the level of the law.Keywords: Protection; Security; Personal Data;E-Commerce.

Analysis of circular economy of E-commerce market based on grey model under the background of big data

PurposeIn order to more accurately predict the dynamics of the e-commerce market and increase the comprehensive value of the circular e-commerce industry, proposes to use Grey system theory to analyze the circular economy of the e-commerce market.Design/methodology/approachConstruct a Grey system theory model, analyze the big data of e-commerce and circular economy of the e-commerce market and predict the development potential of China's e-commerce market.FindingsThe results show that the Grey system theory model can play an important role in the data analysis of circular economy of the e-commerce market.Originality/valueUse Grey model to analyze e-commerce data, discover e-commerce market rules and problems and then optimize e-commerce market.

Deep Learning for Customer Churn Prediction in E-Commerce Decision Support

Churn prediction is a Big Data domain, one of the most demanding use cases of recent time. It is also one of the most critical indicators of a healthy and growing business, irrespective of the size or channel of sales. This paper aims to develop a deep learning model for customers’ churn prediction in e-commerce, which is the main contribution of the article. The experiment was performed over real e-commerce data where 75% of buyers are one-off customers. The prediction based on this business specificity (many one-off customers and very few regular ones) is extremely challenging and, in a natural way, must be inaccurate to a certain ex-tent. Looking from another perspective, correct prediction and subsequent actions resulting in a higher customer retention are very attractive for overall business performance. In such a case, predictions with 74% accuracy, 78% precision, and 68% recall are very promising. Also, the paper fills a research gap and contrib-utes to the existing literature in the area of developing a customer churn prediction method for the retail sector by using deep learning tools based on customer churn and the full history of each customer’s transactions.

Local Anomaly Detection for Multivariate Time Series by Temporal Dependency Based on Poisson Model.

Multivariate time series data are invasive in different domains, ranging from data center supervision and e-commerce data to financial transactions. This kind of data presents an important challenge for anomaly detection due to the temporal dependency aspect of its observations. In this article, we investigate the problem of unsupervised local anomaly detection in multivariate time series data from temporal modeling and residual analysis perspectives. The residual analysis has been shown to be effective in classical anomaly detection problems. However, it is a nontrivial task in multivariate time series as the temporal dependency between the time series observations complicates the residual modeling process. Methodologically, we propose a unified learning framework to characterize the residuals and their coherence with the temporal aspect of the whole multivariate time series. Experiments on real-world datasets are provided showing the effectiveness of the proposed algorithm.

Developing Turkish sentiment analysis models using machine learning and e-commerce data

With the increment of Internet usage, there has been a significant increase in the access and interaction of users in social media, blogs, forums, and criticism sites recently. With social media, access to a large amount of data on various products, services, social and political events is provided. Important feedback about products and services can be obtained as a result of analyzing such data. This study aims to determine the sentiments expressed via texts on social media using machine learning methods. As a result of initial research, it is determined that the best case in which texts and emotions match was the product reviews and ratings used on e-commerce websites. Reviews on different products along with review scores from an e-commerce website have been converted into a table to be used in the machine learning-based sentiment analysis models. Reviews have been classified into three groups as positive, negative, and neutral using the review scores. Considering this claim, Turkish sentiment analysis models were developed using support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and k-nearest neighbors (KNN). Cross-validation results on independent test data taken from the same e-commerce website show that the SVM-based and RF-based sentiment analysis models outperform the other models. In more detail, there is no strict order between SVM-based and RF-based prediction models, but the results of the SVM-based and RF-based models, in general, are the highest or, in the worst case, similar if we compare them with the scores obtained by using the DT-based, LR-based, and KNN-based models. It can be concluded that SVM and RF are viable methods that can be used to classify product reviews into three groups as positive, negative, and neutral within acceptable error rates.

Research on Machine Vision Effect Based on Graph Neural Network Decision

With the continuous expansion of the scale of the network, modeling the complex graph structure is a major challenge for the recommendation task. There are conflicts between these complex information, which will directly affect the recommendation results. For this reason, a graph neural network recommendation method based on multi-branch decision is proposed. The algorithm models the social network graph and the user project graph through the neural network, connects the two graphs intrinsically, and learns the feature vectors of the target users in the social space and the project space. Then two feature vectors are connected in series by MLP to extract the potential feature vector of the user. Finally, the prediction score is generated by integrating the probability matrix decomposition model. In this method, the graph neural network is used to model the program data and dependence graph, and the effective program features are automatically extracted from the source code, and then the extracted features are input into the downstream model for loop vectorization parameter prediction. Finally, the attention mechanism is used for information fusion to get the final session representation and predict the next interactive item. Comparative experiments are carried out under the two scenarios of e-commerce and civil aviation respectively. The experimental results show that, compared with the optimal benchmark model, the improvement of MGSP model on each index of e-commerce data set is more than 1%, and that of civil aviation data set is about 3%, which verifies the effectiveness of MGSP model. On the LLVM cyclic vector test set, the proposed method achieves a speedup of 2.08 times and improves the performance by 12% compared with the existing methods. In order to solve the problem that the existing deep learning model considers the program code as a serial sequence and misses a large performance optimization space, a new program heuristic method based on depth map network is proposed to achieve optimization.

The Impact of Emerging Technologies on Data Mining

Business analytics has improved tremendously in recent past providing business leaders’ insights, particularly from operational data stored in transactional system. An example is e-commerce data analysis, which has recently come to be viewed as a killer appropriate for the field of data mining.

Data Mining Technology in Business Data Analysis

With the vigorous development of e-commerce, people pay more and more attention to data mining technology. This research mainly discusses the application of data mining technology in business data analysis. This study uses the clustering algorithm of buyers’ purchasing behavior as an example to illustrate the definition of VMML in the clustering analysis of purchasing behavior. In this piece of XML, through the integration of data, an e-commerce research data warehouse is constructed, which is also used as the source data of EBizDAS. A certain amount of research has been done on buyers, sellers, commodities and transaction data, and the results obtained by EBizDAS analysis are displayed on the C2C e-commerce data analysis web platform for C2C users to browse and reference online. In this study, the 10 queries in CoHadoop took a total of 849 seconds, while the distributed strategy took a total of 748 seconds, with a performance improvement of about 12%, and the overall performance improvement was still considerable. This research has positive significance for the development of e-commerce.

Research on APP Intelligent Promotion Decision Aiding System Based on Python Data Analysis and AARRR Model

With the development of AI technology and the current situation of the epidemic, online shopping is increasingly popular all over the world. The mobile phone terminals also occupy a larger share, and the use of various APPs has also emerged rapidly in line with the trend of the times. How big data technology is used to analyze the effective data generated by APPs? The paper conducts research from the following three aspects: (1)Finding out customer’s behavior patterns from the analyzed e-commerce data, and analyzing the reasons for customer churn rate and providing effective marketing strategies for merchants; (2) according to the time dimension, from different time dimension of customer behavior rules, find out customer purchase rules for merchants; (3) from the point of view of commodities, finding out customers’ preferences for different commodities, and give different marketing schemes for commodities with different preferences. Through the three aspects of the study, we use Python for data analysis, combined with AARRR model and traditional expert system, the arctic finally sets up an intelligent decision aid system recommended by APP, the system provides different marketing schemes for merchants. The experiment shows that through data analysis and simulation of the use of an APP, in the experimental environment, the APP can better serve customers under the same conditions, and the transaction rate has increased by 7.3%.

TPGN: A Time-Preference Gate Network for e-commerce purchase intention recognition

The studies on users’ purchase intentions based on e-commerce data are of great significance to marketers, buyers, and society. Current studies on users’ intentions with traditional machine learning methods usually focus on unique features and are time-consuming. Due to the characteristics of user behaviors and the importance of time sequence, deep learning methods are increasingly applied in relevant studies. In the study, in order to predict online user’s purchase intentions, based on Long-Short Term Memory (LSTM) model, we proposed Time-Preference Gate Network (TPGN). A pair of preference gates and a pair of time interval gates are added to the model. The preference gates are used to capture the users’ category preferences at different time and the time interval gates are used to capture the users’ long-term interest. In our model, through coupling the input gate with the forget gate, the parameters of the model are reduced and the performance is improved. In addition, the difference in user gender leads to the difference in the performance. Extended experiments with two real data sets confirmed that our model performed better than other baseline models.

E-Commerce Customer Attraction: Digital Marketing Techniques, Evolution and Dynamics across Firms

The emergence of web analytics software has changed the way marketing is researched, monitored, planned, and managed, which suggests a new dimension of marketing interactions between firms. This paper describes digital marketing results in terms of customer attraction to e-commerce websites from different angles (cross-country, firm type, evolution) and investigates empirically how competitors’ marketing activities affect a focal firm. Using a vector autoregression model applied to data for grocery e-commerce in the US, the UK, and France, we find differences across American and European firms in the composition of digital marketing techniques and the existence of interaction effects across firms.