Surface inspection in hot-rolled steel manufacturing requires decisions about material moving through a production line. A model that distinguishes photographed defects must also handle normal surfaces, changing acquisition conditions and uncertain predictions before its output can support coil release. This paper develops a research framework for adapting ResNet-18 to this setting with limited factory annotations. The proposed pipeline combines line-scan image acquisition, patch classification and a decision policy that assigns cases to pass, human review or hold. The NEU surface defect database supplies source-domain examples, factory images supply a normal class and the target-domain evidence required for deployment. The proposed experiment compares training budgets of 10, 25 and 50 images per class, with separate coils allocated to training, validation and testing. Comparisons distinguish six-class defect recognition from seven-class factory inspection, preventing misleading comparisons between models with different label spaces. Evaluation covers class performance, defect escapes, unnecessary holds, review workload and processing deadlines. The analysis identifies the conditions under which the experiment could support deployment, particularly representative normal data and independent validation of release decisions. No model training or factory trial is reported. The contribution is an experimentally testable inspection framework connecting transfer learning to operational quality control.

Brand endorsement is widely used to build brand awareness and shape brand image. With the development of social media, celebrity endorsement has evolved from a predominantly one-way advertising practice into a more interactive process involving endorsers, brands, fans, and digital platforms. However, controversies surrounding entertainment celebrities can create reputational risks for brands. As a result, sports celebrities have attracted increasing attention as potential endorsers, partly because athletes are often associated with relatively stable public images. Using Sun Yingsha's endorsement of Banmu Huatian as a case, this study examines the relationship from three perspectives: endorser-brand fit, communication influence, and risk management. The case analysis suggests that endorser-brand fit provides a basis for establishing the endorsement relationship, communication influence shapes the reach and commercial impact of the campaign, and risk management is important to the continuity of the partnership. This study provides brands with new insights into endorsements and offers targeted recommendations for endorser-brand fit assessment and reputational risk management.

Bankruptcy prediction sits at the core of credit risk management, yet the ML models now used for it are seldom examined for interpretability. This paper benchmarks five classifiers — Logistic Regression, XGBoost, Support Vector Machine, K-Nearest Neighbors, and a Neural Network — on 78,682 firm-year records of U.S. public companies from 1999 to 2018. Boruta selection screens 36 raw items and accounting ratios down to the informative ones, and class imbalance is tackled with cost-sensitive learning plus a Youden's J threshold. XGBoost attains the highest test AUC (0.8343), trailed by ANN (0.8255) and KNN (0.8149). Retained earnings ratio, market-to-assets, and EBIT emerge from SHAP as the strongest predictors. Across pre-crisis (1999–2006), crisis (2007–2009), and post-crisis (2010–2011) windows, the relative importance of these indicators stays largely unchanged, with retained earnings leading in every period. By pairing strong predictive accuracy with explainable evidence, the study narrows the gap between black-box performance and the transparency expected by lenders and regulators. The resulting framework acts as an auditable early-warning tool that practitioners can both trust and interrogate.

This report examines the impact of Apple's promotional activities on purchase intentions among consumers aged 20–30, focusing on four key areas: physical retail stores, the "Shot on iPhone" campaign, product launch events, and the brand narrative shift from Steve Jobs to Tim Cook. Using a mixed-method approach, the study collected 50 valid questionnaire responses and conducted five semi-structured interviews with young Apple users. Findings indicate that Apple's retail stores enhance brand trust through tangible evidence and atmosphere, yet only 34% of respondents rated the in-store experience as highly impressive. The "Shot on iPhone" campaign effectively communicates creativity and authenticity (60% awareness), but user participation remains low. Product launches generate global excitement and influence purchase decisions, though signs of "innovation fatigue" are evident among younger demographics. The evolution from a revolutionary to a more pragmatic brand narrative reflects Apple's adaptation to a mature smartphone market, but also risks diluting its distinctive appeal. Overall, Apple's value‑bundled marketing positively shapes brand identity and shopping willingness, yet strategic adjustments—such as fostering interactive communities, creating layered recognition for creators, and balancing innovation with practicality—are recommended to sustain engagement and counteract fatigue. This research provides empirical insights into how symbolic values influence consumer behaviour in the premium electronics sector.

This review examines how young consumers choose brands by moving beyond explanations that rely mainly on age. Existing studies treat young consumers as an important market segment, but age alone does not explain why the effect of loyalty is stronger in some product categories than in others. This paper argues that young consumers' brand choice is shaped by three main mechanisms: market and information context, perceived value, and social influence. Market and information context influences what brands consumers notice and encounter. Perceived value explains how consumers judge price, quality, usefulness, and risk. Social influence explains how family, peers, online reviews, and user-generated content shape brand meaning and purchase decisions. The review also argues that product category acts as a boundary condition: routine products, visible identity products, and high-risk information-intensive products activate different decision mechanisms. The paper ends with a framework and future research directions that link consumer behavior to business analytics, including segmentation, prediction, and recommendation systems.

Consumer reviews and influencer posts provide two different views of the same product. This study asks whether either source improves product-sales prediction beyond product attributes. The sample contains 90 skincare products, 3,060 reviews, and 450 influencer posts from Tmall and Taobao. Four OLS models compare a product-control benchmark with review, influencer, and combined feature sets. Category-stratified five-fold cross-validation evaluates held-out products, while HC3 robust standard errors are used for inference. The control model performs best (adjusted R² = 0.651, pooled out-of-fold R² = 0.617, RMSE = 0.470). Adding content features slightly raises unadjusted R² but reduces adjusted and out-of-sample performance, and no focal content coefficient is statistically significant. In this small, platform-concentrated sample, product attributes contain most of the available predictive information. Visible review and influencer signals do not improve sales prediction once controls are included. Because the sales window, temporal order, promotional exposure, and brand strength are unavailable, the findings describe predictive associations rather than causal effects.

The proliferation of platform-based fan communities has transformed how cultural content is produced, consumed, and monetized, yet the relationship between platform payment architectures and the cultural norms that emerge within fan communities remains poorly understood. As platforms increasingly shape not only what fans can pay for but also how payment itself is understood, understanding how payment cultures are generated across different platform environments has become urgent. This study examines how platform monetization policies and fan community norms interact across four platforms—Bilibili, Xiaohongshu, Lofter, and AO3—to generate distinct and self-reinforcing payment cultures. Through a comparative case study design incorporating community observation, textual analysis, and semi-structured interviews with 16 active members, we identify four consumption models arrayed along two axes: consumption drive (commercial vs. affective) and linkage mode (collective vs. atomistic). A self-constructed commercialization index reveals a negative correlation between platform commercialization intensity and perceived community agency, suggesting that less intensive platform governance may paradoxically foster deeper community loyalty on members' own terms. Content creators emerge as pivotal mediators in this bidirectional feedback loop.