Analytics for Cross‐Border E‐Commerce: Inventory Risk Management of an Online Fashion Retailer

Abstract

Problem statement: We present a data‐driven analytics study of a Chinese fashion retailer. The retailer fulfills cross‐border orders using online platforms, but faces inventory problems in its overseas warehouses, owing to operational complexities, such as extensive product offerings, high demand risks, and tax risks in cross‐border trade. Traditional approaches (e.g., model‐driven approaches) often fail to provide effective solutions. Therefore, this study proposes a new data‐driven approach to manage inventory in overseas warehouses. Methodology: A two‐stage predictive analytics approach is implemented, as follows: (i) all items are classified into one of two classes, where scriptA‐items are profitable to store in overseas warehouses, but scriptB‐items are not; (ii) the demand levels of SKUs of scriptA‐items are predicted. In the subsequent prescriptive analytics, models are proposed for optimizing inventory decisions related to scriptA‐items. These include a deterministic model that uses the predicted demand as the true demand, and a stochastic model that treats the true demand as a random variable. Results: (i) Using a variety of machine learning techniques in the predictive analytics phase, we find the random forest outperforms other methods. (ii) The deterministic model can be solved as a linear program, and the stochastic model with maximum entropy distributions can be solved using Karush–Kuhn–Tucker conditions. (iii) An application of our results shows that the predictive classification reduces costs (an average cost reduction of up to 20%) by avoid shipping unprofitable items to overseas warehouses. Furthermore, the stochastic model provides near‐optimal solutions (the smallest performance loss is just 0.00%).

Cross-Border E-Commerce Supply Chain Risk Evaluation with FUZZY-ISM Model

“…Van Heel et al [41] studied cross-border e-commerce export trade and found that there are obstacles in customs clearance, logistics, and supervision. Shi et al [42] conducted a data-driven analysis and research on Chinese fashion retailers and found that the risks affecting the cross-border e-commerce supply chain of enterprises include online marketing risks, cross-border e-payment risks, e-customs clearance risks, cross-border logistics risks, and credit risk. Nuruzzaman and Weber [43] have employed the qualitative research methods to identify some key issues such as supply chain facility, inventory management, and legal obstacles with today's supply chain performance of international e-commerce.…”

“…Sometimes, the companies do not have a strong awareness of intellectual property rights and do not know much about overseas laws; infringed persons use e-commerce platforms to carry out phishing law enforcement, freeze the accounts of companies or clear their accounts, and put companies in a difficult position Cross-border transaction risk [1,5,40,[42][43][44] Credit risk C4…”

“…In the field of cross-border e-commerce, international payments are basically monopolized by international credit organizations and international payment companies, and their payment procedures are relatively expensive; most payment tools in China are not recognized by overseas users; cross-border payment channels are not smooth, cross-border e-commerce foreign exchange settlement is prone to problems, and corporate funds cannot be withdrawn, resulting in cross-border e-commerce companies operating difficulties Customs clearance risk [9, 40-42, 44, 45] Customs clearance risk C7 [1,4,8,9,12,[40][41][42][43][44][45] Logistics timeliness risk C10…”

Review of Cross-Border E-Commerce and Directions for Future Research

“…On the other hand, e-commerce characteristics are tied to online transactions and payment, so the issue of cybersecurity and privacy emerges as a significant problem (Zhong et al, 2020). With consumers compelled to surrender their personal information during transactions such as names, location, and bank accounts to facilitate payment, their privacy is put at risk, and such information can fall into unintended individuals' hands (Shi et al, 2020). Conversely, with almost all transactions taking place online, there is always the threat of cyberattacks.…”

The Impact of Organizational Context on the Levels of Cross-Border E-Commerce Adoption in Chinese SMEs: The Moderating Role of Environmental Context

“…With this huge potential of opportunities for SMEs in CBEC, it is reasonable to understand the drivers, motivators, and even mitigating factors of CBEC adoption [3]. In the past, several studies on technological adoption have been conducted by scholars (e.g., [3,[10][11][12][13][14], etc. ); however, limited studies have considered the moderating role of potential variables that may mitigate the relationship of CBEC adoption [4,[15][16][17].…”