E-commerce Data Research Articles

The application of business intelligence system based on big data in e-commerce data analysis

In the face of the rapid development of modern science and technology, in order to ensure that the commercial level is in line with The Times, we need to change the traditional operation mode, and fully apply the science and technology to the e-commerce data analysis. Nowadays, driven by the era of big data development, social process, bring new changes to daily life, consumption, such as electricity is a new product, as the latest business model in modern society, has an important impact on market development, want to ensure electricity enterprises can meet the demand of social development, then from the perspective of electricity data analysis, effectively grasp the market changes, so as to more effective to carry out subsequent work, to fundamentally improve the comprehensive competitiveness of electricity enterprises in the modern market. In view of this, in order that the article wants to ensure the smooth progress of the e-commerce data analysis work, it should start with the business intelligence system under the background of big data, and combine it to ensure the steady development of the e-commerce industry.

Poverty prediction using E-commerce dataset and filter-based feature selection approach

Poverty is a problem that occurs in many countries, notably in Indonesia. The common methods used to obtain poverty information are surveys and censuses. However, this process takes a long time and uses a lot of human resources. On the other hand, governments and policymakers need a faster approach to know social-economic conditions for area development plans. Hence, in this paper, we develop e-commerce data and machine learning algorithms as a proxy for poverty levels that can provide faster information than surveys or censuses. The e-commerce dataset is used and this high-dimensional data becomes a challenge. Hence, feature selection algorithms are employed to determine the best features before building a machine learning model. Furthermore, three machine learning algorithms such as support vector regression, linear regression, and k-nearest neighbor are compared to predict the poverty rate. Hence, the contribution of this paper is to propose the combination of statistical-based feature selection and machine learning algorithms to predict the poverty rate based on e-commerce data. According to the experimental results, the combination of f-score feature selection and support vector regression surpasses other methods. It shows that e-commerce data and machine learning algorithms can be potentially used as a proxy for predicting poverty.

Real-Time Monitoring of Data Pipelines: Exploring and Experimentally Proving that the Continuous Monitoring in Data Pipelines Reduces Cost and Elevates Quality

Data pipelines are crucial for processing and transforming data in various domains, including finance, healthcare, and e-commerce. Ensuring the reliability and accuracy of data pipelines is of utmost importance to maintain data integrity and make informed business decisions. In this paper, we explore the significance of continuous monitoring in data pipelines and its contribution to data observability. This work discusses the challenges associated with monitoring data pipelines in real-time, propose a framework for real-time monitoring, and highlight its benefits in enhancing data observability. The findings of this work emphasize the need for organizations to adopt continuous monitoring practices to ensure data quality, detect anomalies, and improve overall system performance.

AI-Driven Personalized Marketing Strategies: Leveraging IoT and Big Data in E-Commerce

AI-Driven Personalized Marketing Strategies: Leveraging IoT and Big Data in E-Commerce

Prioritizing big data applications in E-commerce considering sustainable development indicators

During the Covid-19 pandemic, when strict restrictions were imposed to protect public health, e-commerce played a significant role in providing products on time. E-commerce technology and big data analytics enable companies to gain competitive advantages and respond to customers more efficiently. To make e-commerce more sustainable, the three dimensions of sustainability must be met, otherwise it can have negative consequences that lead to ecosystem destruction. Thus, e-commerce must learn how to effectively manage certain aspects of sustainability and adapt its operations to achieve balance. E-commerce's impact on sustainability can be measured in three pillars: economic, social and environmental and achieving a balance among these is the ultimate goal of sustainable development. Although the sustainability issue and big data analytics have gained increasing popularity in recent years, there is still a gap in evaluating applications of big data based on sustainable development indicators. In this study, we used a hybrid multi-criteria decision-making technique combining fuzzy TOPSIS and BWM to assess big data applications in e-commerce considering sustainable development indicators. The results showed environmental sustainability and energy consumption efficiency received the highest weight for the main pillars and sub criteria of sustainability indicators. Coordinating and monitoring supply chain processes, innovating product, process and business models, and creating new products and services are the top three applications of big data in e-commerce considering sustainable development indicators. E-commerce managers and experts can make better decisions about sustainable approaches by prioritizing big data applications based on sustainable development indicators. In addition, the proposed approach can also be used to evaluate big data analytics in other industries that consider sustainable development indicators.

Rural E-commerce data analysis based on data mining and its enlightenment to rural digital economy management

Rural E-commerce data analysis based on data mining and its enlightenment to rural digital economy management

Rural e-commerce data analysis based on data mining and its enlightenment to rural digital economy management

Rural e-commerce data analysis based on data mining and its enlightenment to rural digital economy management

Intelligent Analysis Method of E-Commerce Data Based on Multiple Machine Learning Algorithms

Machine learning algorithm is one of the most popular research fields in the 21st century, and it is widely used in various industries. This paper first discusses the development status, characteristics and intelligent classification technology of e-commerce based on various methods. Then, through statistical analysis of multiple samples, this paper establishes a model to predict the quantity of goods and other time-related changes in the future period of time, and proposes an improved variance estimate to achieve the best effect under different data scenarios. Finally, the experiment proves that the response time of the linear regression algorithm fluctuates between 20ms and 25ms, and the overall fluctuation is small. For different samples, the response time of the linear regression algorithm is maintained in a relatively stable range, showing the stability of different input data. The response time of the decision tree algorithm fluctuates between 28ms and 33ms, showing a certain fluctuation. For different samples, the response time of decision tree algorithm fluctuates greatly, which may be affected by the characteristics of input data and show different processing efficiency. The response time of support vector machine algorithm fluctuates between 14ms and 18ms, and the change is relatively stable. For different samples, the response time of SVM algorithm is kept at a relatively stable level, showing the consistency of input data processing ability.

Retracted: A Study on Resource Security under Legal Protection of e-Commerce Data Sovereignty Based on Blockchain Network

Retracted: A Study on Resource Security under Legal Protection of e-Commerce Data Sovereignty Based on Blockchain Network

Context-Aware Personalization: A Systems Engineering Framework

This study proposes a framework for a systems engineering-based approach to context-aware personalization, which is applied to e-commerce through the understanding and modeling of user behavior from their interactions with sales channels and media. The framework is practical and built on systems engineering principles. It combines three conceptual components to produce signals that provide content relevant to the users based on their behavior, thus enhancing their experience. These components are the ‘recognition and knowledge’ of the users and their behavior (persona); the awareness of users’ current contexts; and the comprehension of their situation and projection of their future status (intent prediction). The persona generator is implemented by leveraging an unsupervised machine learning algorithm to assign users into cohorts and learn cohort behavior while preserving their privacy in an ethical framework. The component of the users’ current context is fulfilled as a microservice that adopts novel e-commerce data interpretations. The best result of 97.3% accuracy for the intent prediction component was obtained by tokenizing categorical features with a pre-trained BERT (bidirectional encoder representations from transformers) model and passing these, as the contextual embedding input, to an LSTM (long short-term memory) neural network. Paired cohort-directed prescriptive action is generated from learned behavior as a recommended alternative to users’ shopping steps. The practical implementation of this e-commerce personalization framework is demonstrated in this study through the empirical evaluation of experimental results.

Poverty Level Prediction Based on E-Commerce Data Using Naïve Bayes Algorithm and Similarity-Based Feature Selection

The poverty rate is an important measure of any country because it indicates how well the economy develops and how well the economic prosperity distributes among citizens. The Central Statistics Agency, or BPS, measures the poverty rates in Indonesia using the concept of the ability to meet demands (basic needs approach). Using this approach, spending becomes a measure of poverty, defined as an economic incapacity to satisfy food and non-food requirements. Thus, the poor are individuals whose monthly per capita spending is less than the poverty threshold. In this study, the machine learning method using Naive Bayes with similarity-based feature selection and e-commerce data has been proposed to predict the poverty level in Indonesia. We proposed the method to be used as a complement to the results of the costly surveys and censuses conducted by BPS. Our experiments show that the classifier shows little relevance between the predicted and the original values or actual poverty prediction based on BPS data. A limited number of features does not necessarily result in poor accuracy, however great accuracy is not always achieved if a lot of features are being used.

An Electronic Commerce Big Data Analytics Architecture and Platform

The COVID-19 pandemic significantly increased e-commerce growth, adding more than 218 billion US dollars to the United States e-commerce sales. With this significant growth, various operational challenges have appeared, including logistic difficulties and customer satisfaction. Businesses that strive to take advantage of increased e-commerce growth must understand data and rely on e-commerce analytics. The large scale of e-commerce data requires sophisticated information technology techniques and cyber-infrastructure to leverage and analyze. This study presents a big e-commerce data platform to address several challenges in e-commerce. The presented platform’s design is based on a distributed system architecture that supports e-commerce analytics applications using historical and real-time data and features a continuous feedback loop to observe the decision-making and evaluation processes to achieve the desired objectives. The platform was validated using two analytical applications. The first application was to identify the periods in which customers prefer to place orders, while the second was used to verify the big e-commerce data platform. The resulting insights and findings promote informed e-commerce decisions. Furthermore, viewing and acting on insight results and findings promote informed decisions that potentially benefit the e-commerce industry. The proposed platform can perform numerous e-commerce applications that potentially benefit the e-commerce industry.

Analysis of people’s opinions based on the vaccination procedure and e-commerce product reviews using XLnet framework

Many people have been severely affected by the COVID-19 outbreak, which has left them anxious, terrified, and other difficult feelings. Since the introduction of coronavirus vaccinations, people’s emotional spectrum has broadened and become more sophisticated.We want to observe and interpret their sentiments using deep learning techniques in this work. The most efficient way to convey one’s thoughts and feelings right now is via social media, and using Twitter may help one better understand what is popular and what is going through other people’s minds. Analyzing and visualization of data play a vital role in Data Science; as customers over e-commerce increase, feedback/reviews shared by them increase significantly, and decisions by a new customer to buy a product or not rely on these reviews; reviews might falsely be displayed which may be involving in controlling if any products demand and supply so, reviews analyzing and visualizationto understand they are genuinely playing an important role over e-commerce nowadays. Our primary objective in conducting this study was to understand better the various perspectives individuals held on the vaccination process and reviews of products purchased online. As shown by the presented study, analysis and visualization approaches may be used to facilitate rapid and easy comprehension of e-commerce data, despite its high dimensionality.All correlation and non-correlation factors were mapped and examined, providing a comprehensive picture of the proposed data and its connection to other parameters.The proposed work provides an overview of sentiment observations across arguments and the relationships between parameters; it opens the door for modeling to extract some decision-making insights from the data, which can be used to improve the efficiency of application areas like product quality and customer satisfaction.

Estimating package arrival time via heterogeneous hypergraph neural network

Estimated Time of Arrival (ETA) for packages plays an essential role in intelligent logistics. As a classic ETA method, Origin–Destination-based (OD-based) ETA predicts the delivery time only based on the attributes (i.e., sender address, receiver address, seller, and payment time) of packages under the condition that the delivery route is unavailable. However, existing OD-based methods only exploit attributes associated with an individual order, which fails to model the higher-order interactions within orders and attributes, and fail to sufficiently exploit the graph-structure knowledge (i.e., relation of orders and attributes) and feature-based knowledge (i.e., statistical properties) of orders simultaneously, resulting in inaccurate predictions. In this paper, we propose a novel Heterogeneous HyperGraph Neural Network (H2GNN) for estimating package arrival time. Specifically, to better capture the high-order interactions within orders and attributes, we construct an order heterogeneous hypergraph that utilizes hyperedges to represent orders and nodes to represent order attributes. Besides, we extend the hypergraph learning for large-scale e-commerce data by Hyper-GraphSAGE. Overall, H2GNN can provide informatively representations of packages while preserving both structure-based knowledge learned by hypergraph and feature-based knowledge captured by Transformer. Experimental results on large-scale Alibaba logistics data demonstrate the superior performance of H2GNN compared to the baselines.

The Application of Big Data Technology in the Efficient Development of Cross-Border E-Commerce Industry

Abstract As a typical ecology of “Internet+”, cross-border e-commerce enterprises have a huge amount of data, but it is difficult to use it effectively. This paper researches the generation and development of cross-border e-commerce big data, proposes the association rule algorithm based on Apriori to mine and analyze the cross-border e-commerce data, improves the problem of high time cost of Apriori algorithm, optimizes the clustering analysis method of quantitative attributes, and adopts the distance-based quantitative association rule to search for frequent classes, and analyzes the big data of cross-border e-commerce platforms based on the improved algorithm. Big data of cross-border e-commerce platform. Based on the analysis of the high demand of the cross-border e-commerce platform based on big data, the prediction error rate is 1.75%, 2.27%, 5.48%, 2.49%, 2.91%, 2.08%, 10.18% and 1.81% in order. In terms of user portraits, the accuracy of big data analysis of users’ purchasing power, purchasing habits and consumption intentions reached 86.10%, 73.43% and 90.48% on average. Big data technology helps cross-border e-commerce companies optimize the industry chain, improve operational management efficiency, enhance consumer experience and establish a brand effect.

Unraveling the Impact of Lockdowns on E-commerce: An Empirical Analysis of Google Analytics Data during 2019–2022

This paper presents an empirical analysis of e-commerce data obtained through Google Analytics (GA) from two small businesses’ perspectives: an IT components company and a tourism agency website located within the same county in Romania. The objective of our study is to examine the enduring effects of the COVID-19 pandemic and seasonal variations over the last four years. The data collection spanned from January 2019, predating the onset of the COVID-19 pandemic, until mid-February 2023. To facilitate our analysis, we categorize the GA metrics into groups that encompassed website performance, site accessibility, and user behavior for the IT company. As for the tourism agency, we focus on website accessibility, user behavior, and marketing campaigns. Our goal is to empirically group or associate GA metrics according to their intrinsic meaning and check if each group reflects a certain latent concept (such as user behavior or site accessibility). Furthermore, our study aims to formulate and test five hypotheses regarding the immediate and long-lasting impact of the COVID-19 pandemic on the operations of small businesses. Our contribution consists of formulating and verifying the five hypotheses by providing descriptive data from the results of the Pearson correlation test, empirically grouping the GA metrics and verifying whether they reflect certain latent factors or topics, interpreting the results from the application of the ANOVA technique and Scarpello’s adaptation of the one factor test, respectively.

A hypergraph model of product function recombination based on online reviews

ABSTRACT Functional module recombination is a common means for manufacturers to upgrade and launch new product quickly. However, this method may bring with significant risks and it requires accurate identification on market trends in the uncertain environments, and cannot be achieved depend on expert experience. Therefore, a data-driven approach is proposed for product function recombination based on online reviews. Firstly, the information collection for e-commerce data is carried out to obtain product functional description, and the incidence matrix (IM) is formed by combining the corresponding relationship between function and product, so as to construct the hypergraph model. After that, for calculating the hyperedge weight and hyperedge degree as well as the hypernode weight and hypernode degree, random walk algorithm is introduced to obtain the transition probability between the function nodes. Moreover, three innovation strategies of product function recombination are proposed, including function expand, function trim and function replace respectively. Meanwhile, through the results of transition probability calculation, quantitative analysis is utilised for the implementation of different strategies. Finally, the headphone is taken as a case to verify the method, which is indicated as an effective functional optimisation tool and can provide a new research basis for product design.

Research on Consumer Behavior Prediction Based on E-commerce Data Analysis

The user behavior log of e-commerce platform contains a wide range of data, which can be roughly divided into three types: user basic information, merchant information and user behavior information. Behavioral information includes clicks, favorites, shopping carts and purchases. Because of the asymmetry of online shopping information, the virtuality of trading environment, the incomplete perception of goods and the unsynchronization of trading process, consumers are faced with many uncertainties in the process of online shopping. According to the specific research problems, this paper applies the real consumer behavior data in the e-commerce data platform to build a model to predict consumer behavior. The consumer behavior sequence and other characteristics are analyzed by two machine learning methods respectively. First, the consumer behavior sequence based on time sequence is analyzed. Add the obtained probability value as a new feature to other feature sets as the input of NB (Naive Bayes) model, and train the model to get the probability of whether consumers will buy, and then get the final judgment result of the model. The results show that the fusion model has a balanced performance for consumer behavior sequences with different lengths, and its accuracy can be kept at around 0.9. The research on the problems raised in this paper can also be extended to other fields.

Social inequality of urban park use during the COVID-19 pandemic

Although many studies have examined social inequalities related to urban parks, there is limited knowledge about the social inequalities of urban park use during crises. By integrating a large amount of mobile phone data and e-commerce user data, this study tracked 81,350 anonymized individuals’ urban park use behavior in Shenzhen, China, from 2019 to 2021, covering a period before and after the start of the COVID-19 pandemic. Results reveal that while most of the parks saw a reduction of over 50% in the number of visitors, some parks, especially relatively small and remote parks, had more visitors after the pandemic began than before. In addition, COVID-19 has caused residents’ urban parks use time to decrease and such impacts are more severe in vulnerable groups (e.g., females, the elderly, juveniles, and low-income groups). Moreover, there are significant inequalities in urban park use between rich and poor communities, and COVID-19 has slightly exacerbated these inequalities. The study highlighted that integrating mobile phone data with e-commerce data is an effective way to unveil the complex social inequalities behind human behavior. Findings could help to improve social equality in urban park use as well as providing insights for evidence-informed decision-making in post-pandemic recovery and future crises.

A Dynamic Export Product Sales Forecasting Model Based on Controllable Relevance Big Data for Cross-Border E-Commerce

Abstract To improve the prediction accuracy of export product sales, this paper constructs a dynamic export product sales prediction model based on controlled relevance big data for cross-border e-commerce to improve sales prediction’s scalability and dynamic evolution. Based on the traditional prediction model, a big data controllable clustering algorithm is used to divide the data into several macro-clusters by data dimensions to determine the number of class clusters and the location of centroids. The K-mean algorithm is used to estimate and categorize the indicators affecting the prediction online, to dig out the key factors affecting the prediction of export product sales, and to establish a dynamic prediction model. The analysis results show that the plausibility measure of the proposed model is 21.9, and the error coefficient is 5.1, which are the smaller values in the reference interval. The average prediction error ratio is 2.25%, the average confidence level is 93.05%, and the error efficiency between predicted sales and actual sales is only 0.98%. Thus, the prediction model proposed in this paper improves the prediction effect of export product sales and has high practical value.