Clothing E-commerce Research Articles

E-commerce clothing review analysis by advanced ML Algorithms

A significant aspect in the rapid ascent of Bangladesh's e-commerce sector in recent years has been the significance of consumer evaluations. By examining these reviews, readers can gain enhanced insight into consumer happiness and product quality. This research analyses the sentiment of online clothes reviews with advanced machine-learning techniques. The fundamental purpose of evaluating several machine learning models, such as KNN, RF, XGB, Multi, LSTM, and CNN, is to identify the most effective method for sentiment classification. Following the compilation of an extensive dataset of clothing assessments and the execution of data preparation tasks, including cleaning, tokenization, and stop word elimination, we utilised a combination of deep learning and machine learning models for classification purposes. KNN had the highest accuracy in forecasting the future attitudes of the models evaluated. The findings indicate in the 5000 datasets that KNN is the most effective algorithm for assessing the sentiment of online purchasing reviews. KNN reached at 0.91% Accuracy. This project's automated and scalable methodology may enable online businesses to evaluate client feedback and make more informed decisions. Future research initiatives encompass augmenting the dataset, experimenting with various methods, and incorporating these models into AI-driven mobile and online applications for real-time sentiment analysis.

Comparative Study among Term Frequency-Inverse Document Frequency and Count Vectorizer towards K Nearest Neighbor and Decision Tree Classifiers for Text Dataset

Background: Text classification techniques are increasingly important with the exponential growth of textual data on the internet. Term Frequency-Inverse Document Frequency (TF-IDF) and Count Vectorizer(CV) are commonly used methods for feature extraction. TF-IDF assigning weights to terms based on their frequency. CV simply counts the occurrences of terms. The performance of CV as well as TF-IDF are evaluated and compared with KNN and DT classifiers across text datasets. Methodology: The investigation begins with preprocessing. The feature vectors are created using both TF-IDF and CV. Feature vectors are passed into the KNN and DT classifiers at in training stage. Experiments are executed the usage of Kaggle's public database Ukraine 10K tweets sentiment_analysis dataset and the Womens ecommerce clothing reviews dataset. Findings: The average of precision, recall, f1 score and accuracy of KNN with TF-IDF were 84.5%, 87%, 83%, 87% respectively and KNN with CV were 83.5%, 87%, 83.5%, 87% respectively. Similarly, average of precision, recall, f1 score and accuracy of DT with TF-IDF were 89%, 89%, 89%, 89% respectively and DT with CV were 89%, 89.5%, 89.5%, 89.5% respectively. The results obtained in this research is consistent with previous similar research result. Conclusions: The performance of TF-IDF is almost similar as CV for a particular dataset and a particular classifier in this study. Novelty: The experiment performed using these classifiers and feature extraction methods on the datasets is a novelty and contribution of this research.

Examining The Impact of Social Media Marketing Perceptions on Purchase Intention Through Persona Clustering in E-Commerce Clothing Line

Examining The Impact of Social Media Marketing Perceptions on Purchase Intention Through Persona Clustering in E-Commerce Clothing Line

Enhancing E-commerce Recommendations: Unveiling Insights from Customer Reviews with BERTFusionDNN

In the domain of e-commerce, customer reviews wield significant influence over business strategies. Despite the existence of various recommendation methodologies like collaborative filtering and deep learning, they often encounter difficulties in accurately analyzing sentiment and semantics within customer feedback. Addressing these challenges head-on, this paper introduces BERTFusionDNN, a novel framework merging BERT for extracting textual features and a Deep Neural Network for integrating numerical features. We assess the efficacy of our approach using a Women Clothing E-Commerce dataset, benchmarking it against established techniques. Our method adeptly extracts valuable insights from customer reviews, fortifying e-commerce recommendation systems by surmounting barriers associated with deciphering both textual nuances and numerical intricacies. Through this endeavor, we pave the way for more robust and effective strategies in leveraging customer feedback to optimize e-commerce experiences and drive business success.

Research on Clothing Brand Marketing Strategy Based on E-commerce Webcasting in the Internet Era

Abstract In recent years, with the rapid development of the Internet, e-commerce webcasting, as a new type of marketing method, has gradually been favored by clothing brands. The study constructed a model of factors influencing consumer purchase intention in live broadcasting e-commerce based on the SOR model, followed by hypotheses. An empirical study was conducted by distributing questionnaires to the consumer population watching live e-commerce streams. This paper recovered 388 valid questionnaires and used the PLS-SEM structural analysis method and factor analysis to conduct relevant test studies on each of the proposed variables. The empirical study of the five stimulus variables through structural equations concludes that all five stimulus variables are impacted by consumers’ purchase intention, with situational characteristics having the most significant impact on consumers’ perceived pleasure. Lastly, the derived influencing factors confirm the results. The proposal suggests a strategic approach to enhance the marketing of e-commerce clothing brands.

Transformer Based Unsupervised Learning Approach for Imbalanced Text Sentiment Analysis of E-Commerce Reviews

In e-commerce, online reviews play a vital role in understanding customer requirements. Companies can perform analysis of these reviews to make right business decisions. However, manually analyzing the content generated by each user on social media is challenging due to its high volume and frequency. Sentiment analysis (SA) is a Natural Language Processing (NLP) technique which provides an automated solution to this problem. It is a challenging subtask of text classification. Over a long time, researchers have proposed different approaches to solve it. This paper proposes an unsupervised learning approach using transformer architecture to perform SA on women’s clothing e-commerce dataset which is imbalanced in nature. In this study, we have fine-tuned DistilBERT, a cutting-edge transformer based pre-trained model and developed models for two subtasks of SA named as Sentiment Classification (SC) and Product Recommendation (PR). The proposed models have achieved the highest F1 scores (0.79 for SC and 0.85 for PR), AUC scores (0.98 for SC and 0.96 for PR) along with the highest accuracy of 0.96 for SC and 0.91 for PR. We found that the performance of our models is least affected by imbalanced dataset issues. The results show that the proposed models have significantly outperformed the traditional supervised approaches and various other existing state-of-the-art (SOTA) models. This study can contribute to a better understanding of consumer sentiment and consumer psychology in the e-commerce transaction business.

APLIKASI E-COMMERCE PAKAIAN BERBASIS ANDROID MENGGUNAKAN METODE PROTOTYPE

E-commerce is a profitable opportunity for SMEs, particularly in the sale of household goods like clothing. SMEs' growth in e-commerce has been driven by theCovid-19 pandemic, leading to widespread adoption ofe-commerce systems. OvintLevint, a clothing store thatstarted during the pandemic, still relies on traditionalmarketing methods like word-of-mouthrecommendations. This hampers their growth andcompetitiveness against well-known brands, requiringsignificant investment and time to overcome. Currently, OvintLevint accepts both cash and non-cashtransactions, including transfers and WhatsApp-basedpayment proofs. However, there are frequent instancesof lost transaction receipts and income recording errors. To facilitate customers and OvintLevint, an Android system is being developed for online product purchases. Equipped with a payment gateway, this system aims tosimplify customer transactions. The development usesprototyping with the Flutter framework (Dart andjQuery) for frontend, and Laravel framework (PHP andBootstrap) for backend and web administrationservices. Research findings suggest that developing a clothing e-commerce application can streamline theordering process, transaction data processing, andenhance marketing efforts.

Recognition of fabric composition of clothing in an image in e-commerce using neural networks

Objectives. Development of new approach for recognizing the fabric composition of clothing in e-commerce images by using generative adversarial network(GAN) to generate synthetic images of clothing with known fabric composition, to be used to train the CNN to classify the fabric composition of real clothing images. Instead of a classic clothing image, a copy is generated with the material zoomed to fibers and fabric structure.Methods. The main methods to recognize the fabric composition of the clothing image in the e-commerce are the creation and annotation of a dataset for the neural network training, synthesis of the fabric of clothing, the choice of architecture and its modification, validation and testing, and interpretation of the results.Results. Experimental results with the constructed method show that it is effective for accurately recognizing the fabric composition of e-commerce clothing to be used to improve search and browsing on websites.Conclusion. In the course of the experiment, using a generative adversarial network, a data set of e-commerce products was synthesized and annotated, neural networks were built to recognize the composition of the fabric of clothing items. The results of the study showed that the new approach for recognizing the fabric of clothing provides higher accuracy in comparison with already known methods, in addition, the use of the attention model also gives good results to improve the metrics.

Examining Women’s E-Commerce Clothing Reviews

Due to the outbreak of the epidemic in recent years, the development of e-commerce has led to a golden age. However, since customers can't personally articulate their product dissatisfaction or satisfaction to the store, the review section has become a place where customers often discuss or share reviews that help other new customers understand the true condition of each store's products. And e-commerce product reviews are emotionally featured, from which we can extract key emotionally featured words to drive customers' attitudes toward the product. In this study, we will use the Vader function to extract keywords, and then the use polarity score to judge women customers' recommendation index for women's clothing e-commerce platform, and analyze which aspects are the most important for e-commerce store owners to pay attention to and improve in order to convert the bad reviews

Effects of Service Quality on Clothing E-Commerce Customer Satisfaction and E-Brand Loyalty

Effects of Service Quality on Clothing E-Commerce Customer Satisfaction and E-Brand Loyalty

The Progress of Business Analytics and Knowledge Management for Enterprise Performance Using Artificial Intelligence and Man-Machine Coordination

This study aims to explore the integration of human-computer interaction (HCI) technology and platform ecosystem in artificial intelligence (AI) environment, thus providing a practical basis for the intelligent development of strategic management of platform ecosystem. With clothing e-commerce as an example, first, the business model of brand clothing is simply analyzed. Then, the fashion knowledge management method is adopted to build the fashion data warehouse. The platform intelligent clothing ecosystem is innovatively put forward through the research of business analytics and management mode of clothing e-commerce industry. The optimized genetic algorithm is used to solve the objective function of the model, and a flexible production scheduling model with multiple constraints and maximum cost-saving is established. Finally, the questionnaire results of voice interaction users are analyzed by HCI customer trust model.

The Application of Clothing Intelligent 3D Display with Uncertainty Models Technology in Clothing Marketing

As a result of the development of new technologies such as satellite communication, digitalization, and multimedia computer networks, new media such as blogs, online magazines, and wireless network media have sparked a lot of interest. This study uses 3D clothing display technologies to improve the customer experience of online clothing marketing, aid in the improvement of online clothing marketing efficacy, and extensively discuss the digital clothing anthropometric model. Furthermore, this study employs the convex hull approach and NURBS fitting technology to address concerns with digital clothing anthropometric measurement and provides a practical solution for measuring straight line length, circumference length, and curve length. Furthermore, this research incorporates 3D intelligent technology to develop an online fitting system as well as an intelligent display system for garments. The simulation experiment investigation revealed that the smart clothing 3D display system proposed in this work has a substantial impact on growing online e‐commerce clothing marketing as well as improving clothing marketing effectiveness.

A Statistical Analysis of Textual E-Commerce Reviews Using Tree-Based Methods

With the increasing interest in e-commerce shopping, customer reviews have become one of the most important elements that determine customer satisfaction regarding products. This demonstrates the importance of working with Text Mining. This study is based on The Women’s Clothing E-Commerce Reviews database, which consists of reviews written by real customers. The aim of this paper is to conduct a Text Mining approach on a set of customer reviews. Each review was classified as either a positive or negative review by employing a classification method. Four tree-based methods were applied to solve the classification problem, namely Classification Tree, Random Forest, Gradient Boosting and XGBoost. The dataset was categorized into training and test sets. The results indicate that the Random Forest method displays an overfitting, XGBoost displays an overfitting if the number of trees is too high, Classification Tree is good at detecting negative reviews and bad at detecting positive reviews and the Gradient Boosting shows stable values and quality measures above 77% for the test dataset. A consensus between the applied methods is noted for important classification terms.

New fuzzy RFMD model. A method to identify new customer profiles due to an increase in online activity. Case study of a retail business

Gaining customer loyalty has become one of the main objectives of all companies. Retailers, especially the online ones, have the advantage of knowing their customers’ historical purchase data, which provides them with an understanding of the customers’ buying patterns. A widely-used tool in strategic marketing and customer loyalty is segmentation based on the traditional Recency, Frequency and Monetary (RFM) model. Subsequently, the fuzzy RFM model proved to be an improvement on the traditional RFM model. There has been a change in the retail customer profile, with the growth of a new cluster, the “One-Shot Customer”, new customers that buy from a retailer just once and never come back. In response to this change, the fuzzy RFM model has been modified to include a new dimension capturing Length or Duration. This study presents the new fuzzy RFMD model (Recency, Frequency, Monetary and Duration model), which can be used to better identify that new, large group of customers. The paper also provides a case study based on an e-commerce clothing retailer. Its customer database was segmented using the k-means algorithm and the Isolation Forest algorithm was applied to identify and correctly treat possible anomalies. The Customer Lifetime Value and the weights for the RFMD attributes were calculated by applying the Analytic Hierarchy Process (AHP) model. Results reveal the improvement that the weighted fuzzy RFMD model offers to retailers, enabling them to detect the One-Shot Customers and thus optimize their strategic marketing plans.

WITHDRAWN: Women’s e-commerce clothing sentiment analysis by probabilistic model LDA using R-SPARK

In today's fields of education and literature, electronic commerce (e-commerce) is a well-known subject. Excellent research on e-commerce focuses predominantly on developing economies. Customer behavior analysis is gaining more prominence as consumers move from visiting retail shops to shopping online from the e-commerce view. In this article, review is taken into account in the case of sentiment analysis to evaluate, implement and analyse the most effective techniques. In numerous research ventures, including in the area of text classification and information retrieval, probabilistic models currently play a major role. Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Indexing (PLSA) and Latent Dirichlet Allocation (LDA) represent probabilistic models. The LDA approach is used in this paper to define online feedback for sentiment analysis since the LDA approach is intended to address LSA and PLSA issues. Online shopping seems to become a central platform for shoppers with the development of e-commerce, and it is necessary to forecast the scale of e-commerce transactions. This paper is used to scan online data of women's apparel. By encouraging a more custom-made shopping experience, it will boost customer loyalty and sales, resulting in higher retention rates and viable improvement.

Precision Marketing Strategies for Small and Medium-sized Clothing E-commerce Enterprises Based on Big Data

Based on the big data analysis technology of small and medium-sized clothing e-commerce enterprises, this paper provides theoretical and practical methods for e-commerce enterprises to apply big data technology. The data sources come from questionnaires and online data grab. Through the Google online questionnaire survey, 252 valid questionnaires were received. Python is used to search valid reviews on Tmall and Internet with some keywords, and a total of 11,864 valid comments were obtained. We find that the reason why men buy clothes is as high as 68% because of the seasonal change, but only 31% of women buy clothes because of the seasonal change. The higher the average monthly income of women, the more attention is paid to whether the style of clothing design is suitable for themselves, and the more attention is paid to the service attitude of e-commerce enterprises. From decision tree analysis, the fit of clothing style is the most important factor affecting the shopping choice of customers. From the data of customer reviews, the most mentioned variables are clothing style, fashion, service attitude and price. The number of reviews and the sentiment analysis score on clothing style are all ranking first. The number of reviews and the sentiment analysis score on clothing fashion are all ranking second. We also proposes corresponding precision marketing strategies based on the results of big data analysis, such as gender recommendation strategies, personalized recommendation strategies, differentiated marketing strategies, enterprise training and clothing design strategies.

Analysis of Factors Influencing Consumers’ Purchase Intention Based on Perceived Value in E-commerce Clothing Pre-sale Model

Analysis of Factors Influencing Consumers’ Purchase Intention Based on Perceived Value in E-commerce Clothing Pre-sale Model

Garment E-commerce Return and Exchange 4PL Innovation

Starting from the research on the existing problems in the return and exchange process of existing clothing e-commerce, this paper proposes the clothing e-commerce return and exchange 4PL platform innovation mode for the three pain points, namely, the long return and replacement cycle, the out-of-stock in change of season and the insufficient development of the residual value of returned clothing. Based on this, this paper introduces a 4PL-led dual pre-strategy and then expounds the advantages of the dual pre-strategy by means of comparison. At last, this paper describes in detail how to implement the dual pre-strategy under this mode, and constructs the concept model of 4PL platform, thus realizing the optimization of the reverse logistics supply chain of apparel e-commerce.

Application of the analytic hierarchy process in the selection of storage rack systems for e-commerce clothing industry

Purpose- In this study, it was aimed to select the appropriate storage rack system for e-commerce clothing industry, by comparing storage rack systems in terms of criteria such as cost, volume utilization, height utilization, ease of order picking and stock cycle speed. Methodology- First of all a literature review is carried out. Secondly, the comparison of the storage systems is made and the ones that are suitable for the e-commerce sector and that will be included in the AHP (Analytical Hierarchy Process) analysis are determined. Finally, a semistructured interview is done with 3 e-commerce sector representatives and the AHP method is used to analyze the data. Findings- Considering the usage areas, features, advantages and disadvantages; it was decided to include Back-to-Back and Narrow Aisle and Automatic Storage Systems in the AHP analysis. Back-to-Back Rack System was found to be first with 36.2% ratio. Automatic Storage Systems are in the second place due to their cost disadvantage although they are advantageous for all other criteria. Narrow Aisle Rack System is in the third place, although it more cost-effective than the Automatic Storage Systems, it falls behind it in terms of other criteria, especially the inventory cycle speed criterion. Conclusion- As a result of the study using AHP multi-criteria decision-making method, Back-to-Back Rack System was evaluated as the most suitable storage rack system for e-commerce clothing sector.

A Proposed Model for Virtual Fitting Room Based on Usability and Profound Emotional Elements

Technological advancement has evolved the way business is conducted. Companies around the globe venture into e-commerce to reach more customers apart from the traditional retails and marketing approaches. Nowadays, almost everything could be found sold via the internet regardless of size, usage, price and etc. The challenge of e-commerce channel is coming from its inability to provide a practical ways in giving the customers the sense of trying before purchase which is crucial for some product type namely clothing. This paper presents the issues in the e-commerce clothing industry, namely fitting issues and problems encountered in existing Virtual Fitting Room (VFR) applications. These issues include usability and lack of a profound emotional stimulant within existing applications. A systematic procedure of searching related literature on VFR is done based on several identified criteria from the established online repository. The extensive search result is then filtered based on the identified criteria once again to obtain the suitable model to be further studied. This study reviewed five VFR-related models, with the results confirming the issues of usability and profound emotional elements in each model. This study also proposed a new VFR model based on the Unified Theory of Acceptance and Use of Technology (UTAUT), which consists of usability and profound emotional constructs. These elements were mainly included to solve the identified problems and to provide guidelines for a design solution, which is usable, useful, and delightful.