Search Results (9)

This study proposes how to incorporate concurrent purchase data into e-commerce recommendation systems to improve their predictive accuracy. We identified that concurrent purchases account for about $23\%$ of total orders on Katcher’s, a Korean e-commerce platform. Despite the prevalence of concurrent purchases, existing algorithms often overlook this aspect. We introduce a novel transformer-based recommendation algorithm to process a user’s order history, including concurrent purchases. Each order is represented as a natural language sentence, capturing the order timestamp, product names and their attribute values, their corresponding categories, and whether multiple products were purchased together in a single order (i.e., a concurrent purchase). These sentences form a sequence, which serves as a training dataset for fine-tuning Bidirectional Encoder Representations from Transformers (BERT) with the Next Sentence Prediction objective. We validate our ideas by conducting experiments on Katcher’s platform, demonstrating the proposed method’s improved prediction performance compared to existing recommendation systems, with enhanced accuracy and F1 score. Notably, the normalized discounted cumulative gain (NDCG) showed a significant improvement with a large margin. Furthermore, we demonstrate the beneficial impact of integrating concurrent purchase information on prediction performance. Full article

As e-commerce continues to expand, understanding the factors that drive consumer traffic to business-to-consumer (B2C) websites is crucial. This study investigates the interplay between website technological sophistication, brand recognition, and business model innovation in influencing website traffic among Korean B2C companies. Drawing on data from 9003 companies across seven key sectors—finance, retail, healthcare, technology, food, education, and media—we employ Ordinary Least Squares (OLS) regression analysis to test our hypotheses. Our findings reveal that website technological sophistication is positively associated with monthly website visits. This relationship is particularly pronounced for companies with innovative business models, highlighting the synergistic effect of advanced website features and novel business strategies in attracting consumers. Conversely, the positive impact of website technological sophistication on traffic is less significant for well-established brands with high recognition levels, indicating that strong brand equity can mitigate the need for highly sophisticated websites. These results align with the Technology Acceptance Model (TAM), Innovation Diffusion Theory (IDT), and Signaling Theory (ST), providing a nuanced understanding of how technology, branding, and innovation intersect to drive online consumer behavior. Our study offers valuable insights for e-commerce firms seeking to optimize their digital presence and underscores the importance of investing in advanced website functionalities, particularly for lesser-known brands and companies with innovative business models. Future research should explore these dynamics in different cultural and industry contexts to enhance the generalizability of our findings. Full article

South Korea is one of the leading markets for the e-commerce industry. In line with the rapid growth of the e-commerce industry, the parcel delivery volume in Korea has also proliferated. Despite the developments in the Korean e-commerce and courier industries, consumers still experience a high package damage rate. In response, many packaging engineers in Korea have raised the need for new parcel shipping environment tests that reflect the Korean ground shipping environment in order to properly optimize packages. However, only limited information on the Korean parcel shipping environment is currently available. Therefore, this study focused on measuring and analyzing the shock and drop levels that parcels experience during ground shipping in Korea. Shock data were collected from a total of sixty one-way shipments for small, lightweight packages and medium, mid-weight packages. The findings revealed that the two types of boxes do not experience significantly different numbers of shock events or drop heights in the Korean parcel delivery environment. Furthermore, the number of shock events that occur in Korea is substantially less than the international testing standard and less than in previous studies conducted in both Europe and the USA. In contrast, however, the drop heights are higher than those in the international testing standard and previous studies. Shock events were found to occur most frequently on the edges and to be concentrated around the bottoms of the packages. Most shock events happen while packages are loaded and unloaded at hub terminals and sub terminals. Full article

South Korea has one of the largest e-commerce markets in the world. The last-mile delivery segment of e-commerce often causes critical damage to products in protective packages. Despite the rapid growth of the e-commerce market in Korea, the last-mile distribution environment has not yet been thoroughly investigated. The main aim of this study was to provide an understanding of the vibration levels that were measured from various parcel delivery routes within Seoul, Korea, using common types of parcel delivery trucks. Vibration levels of ten delivery trucks were measured and analyzed in terms of power spectral densities (PSDs) and presented as PSD spectra. The last-mile delivery vehicle vibration levels in Korea were found to be consistently lower (in the 1 to 200 Hz frequency range) than those recommended by international standards and lower than the vibration levels of parcel delivery vehicles in the U.S. and Hungary. The results also revealed that the highest intensity peak of the PSD spectrum for Korea was located in the lower frequency range (1.5 to 2 Hz) compared to the ISTA 3A pickup and delivery test profile (3 to 4 Hz) and the test profile recommended for Hungary (13 to 16 Hz). A smoothed composite spectrum was also provided to support Korean packaging engineers in optimizing their packages by simulating proper last-mile truck delivery vibration levels in lab conditions. Full article

The rapid growth of digital trade has had a profound impact on global economies, revolutionizing trading practices and facilitating trade expansion. The purpose of this paper is to explore the digital partnership between Korea and the European Union (EU) and its implications for their shared agenda in digital trade to theorize the dynamics of digital trade. A case study method is used to explore trade between Korea and the EU with in-depth descriptive analysis. Digital trade-flow statistics were analyzed to develop the case for Korea and EU digital trade and derive implications for both countries. The findings were generalized by discussing the relevant literature and data from other countries to identify the wider implications. The analysis was focused on the areas of information and communication technology and e-commerce. The findings suggest uncovered trade imbalances, such as Korea’s surplus of ICT goods exports and the EU’s dominant position in online trade. There is an influence of supply chain dynamics, specifically the presence of Korean manufacturers’ production units in countries like Vietnam, and the same dynamics have shaped Korea’s actual place in the supply of ICT goods to the European market. While the digital partnership was established to align regulatory frameworks and foster trust, transparency, and harmonization in the digital domain, it has failed to adequately reflect the importance of digital trade. Although both sides are motivated to collaborate on the harmonization of digital trade rules, there have been instances where the partners’ interests diverge. It is concluded that some political and economic factors may hinder the effectiveness of the digital partnership, unless concrete measures that go beyond traditional bilateral policymaking approaches are implemented. It is therefore recommended to emphasize the need to enhance the efficacy of the digital partnership by taking bolder actions to develop digital trade. Full article

The Korean e-commerce market represents a large percentage of the global retail distribution market, a market that continues to grow each year, and online payments are rapidly becoming a mainstream payment method. As e-commerce becomes more active, many companies that support electronic payments are increasing the number of franchisees. Electronic payments have become an indispensable part of people’s lives. However, the types of statistical information on the results of electronic payment transactions are not consistent across companies, and it is difficult to automatically determine the error status of a transaction if no one directly confirms the error messages generated during payment. To address these issues, we propose an optimized LSTM model. In this study, we classify the error content in statistical information based on natural language processing to determine the error status of the current failed transaction. We collected 11,865 response messages from various vendors and financial companies and labelled them with an LSTM classifier model to create a dataset. We then trained this dataset with simple RNN, LSTM, and GRU models and compared their performance. The results show that the optimized LSTM model with the attention layer added to the dropout layer and the bidirectional recursive layer achieves an accuracy of about 92% or more. When the model is applied to e-commerce services, any error in the transaction status of the system can be automatically detected by the model. Full article

The Web has provided an increasing proportion of use as a medium for e-commerce in addition to various recommender systems. It can be used for analyzing recommendation system-based feedback (e.g., a form in which a user inputs their preferences for various items as numerical values into a specific evaluation system) to estimate customer interest; in addition, analyzing multi-modal types of feedback (e.g., product purchase traces, inquiry lists, inquiry times, and comments) with deep learning can also be used to estimate user interest. As many companies around the world promote their products through micro-influencers on the Web, related research has continued to predict the purchase conversion rate of the influencer through a variety of technologies. In this work, we present a multi-modal micro-influencer analysis scheme for a marketing maximization strategy. Our scheme uses the multi-modal data stored in Mecha Solution’s own shopping mall of Korea, as well as famous Korean Internet platforms, and Coupang, Naver, and Oliveyoung’s data such as article posting comments and statistics information. By extracting the main characteristics of the real article postings from real users as opposed to those from factitious influencers posting articles and comments and identifying articles other than advertisements, influencer scores are obtained, assuming that articles other than advertisements can further increase the purchase conversion rate. Based on influencer score, we propose a multi-modal micro-influencer analysis scheme that recommends influencers use content-based collaborative filtering and user-based collaborative filtering for items that the influencer has not yet reviewed. The experiment was implemented to prove that the proposed scheme successfully achieves this goal. Full article

This study aims to investigate motivational factors and motivation hindering factors of online shopping via online open market platforms. For a comprehensive exploration, the response data were collected from a total of 417 Korean consumers before conducting a hierarchical regression analysis. The results showed that the effects of motivation factors on purchasing intention were all supported. As for moderating effects of concerns for e-commerce, privacy concerns by time saving, perceived ease of use, and security concerns by cost saving were found to be statistically significant. Privacy concerns by cost saving and business integrity concerns by time saving were also found to be statistically significant, but had a positive effect as opposed to an initial prediction. The finding denotes that, in order to reduce concerns for e-commerce, consumers may prefer using the online shops they can trust based on their previous shopping experience. Various concerns identified and analyzed in this study are clues to better understanding what potentially motivates or obstructs consumers to shop online, thereby helping businesses thrive in the online open market. Full article

Hyperlinks, which connect web pages on the World Wide Web, are rich sources of hidden information. ECommerce Websites, which are created for different purposes from online sales to company promotion, would benefit if they receive more links from other websites as this would lead to increase the traffic to these websites. This paper analyses the structure of e-commerce websites using webometric approach to uncover any hidden information from the hyperlinks. The top 50 retail companies’ e-commerce websites each from Asia Pacific and USA are chosen for this study. Our results found a positive relationship between the external inlinks count pointing to a retail company e-commerce website and one of its business measures, sales. But no association has been found between hyperlink metrics and business measure like revenue. However this conclusion does not hold good for all categories of companies. Comparing the web presence, US private retail companies are more visible on the Web than the Asia pacific retailers. Furthermore this study has found that counts of links pointing to a retail websites are positively correlated with the website age. That is older websites in English language received more external inlinks. Such a correlation does not exist for Japan, China and Korean language websites. Full article