American Journal of Technology

AI-Based Bot Detection for Dynamic Pricing Engine in Retail and Logistics Platforms

2026-01-31T20:46:40+00:00

Aim: Dynamic-pricing services rely on good demand indicators, but the retail and logistics sites continue to be affected by price bots. These automated agents interact with traffic volumes and corrupt the input on price optimization. This study aims to develop and evaluate a hybrid artificial intelligence–based bot-detection framework that identifies automated sessions in retail and logistics platforms and provides explainable traffic-quality signals for dynamic pricing systems.

Methods: The study adopts a system-based experimental design that integrates graph-based modeling, sequence learning, Agentic AI-generated synthetic traces, and ensemble classification. Data were drawn from anonymized web logs, honeypot captures, and multi-agent adversarial simulations. Models are tested in terms of precision, recall, AUC, and stability of the pricing engine.

Results: The proposed pipeline achieved high detection performance (AUC ≈ 0.94) and showed that graph metrics and timing distribution characteristics were the most prominent predictors of automated behavior.

Conclusion: The use of AI-based synthetic traces enhanced the model’s strength, aligning with BotChase and other research studies.

Recommendation: This study suggests that a hybrid AI/ML-based bot detection approach can enhance the reliability of demand signals used in dynamic pricing systems, providing a viable alternative to traditional binary blocking methods. This helps significantly in preventing pricing distortion and enhancing market resilience.

Agentic AI Orchestration Frameworks for Composable Commerce Ecosystems: A Case Study of Enterprise Transformation

2026-02-02T22:50:48+00:00

Aim: Most modern digital commerce is quickly shifting to composable, API-first design which allows organizations to compose best-of-breed capability in terms of content, product data and customer engagement. Though more agile, this modularity adds serious orchestration complexity to distributed systems such as Product Information Management (PIM), Content Management Systems (CMS), and Digital Asset Management (DAM). The aim of this study is to propose and evaluate an AI agentic orchestration framework for composable commerce ecosystems, addressing orchestration complexity in distributed systems.

Methods: Using a design science research methodology, the framework was evaluated through a longitudinal case study of a global electronics company’s platform modernization project that employed a headless architecture integrating Akeneo, Contentstack, Bynder, and Coveo. Quantitative and qualitative data, including deployment rates, development cycle times, revenue metrics, and observations of cross-functional coordination, were collected.

Results: The framework improved deployment rates by at least 40%, reduced development cycle times by 30%, and increased revenue by over 40% during the evaluation period. Qualitative feedback indicated that autonomous orchestration enhanced timeliness and minimized latency in cross-functional coordination.

Conclusion: The study synthesizes empirical evidence to support the proposed framework and offers practical guidance for organizations adopting composable commerce and AI-driven orchestration.

Classification Models to launch the New Pharmaceutical Product / Drug Using SAP ERP Data

2026-01-31T06:45:58+00:00

Aim: This paper examines the potential to improve the early-stage performance of pharmaceutical product launches, particularly within the critical first 3 - 6 months, through the use of supervised machine-learning classification models.

Methods: The study employs supervised machine-learning models, including logistic regression, random forests, and neural networks, implemented on the SAP Business Technology Platform (BTP). These models integrate SAP S/4HANA transactional data with external market indicators to optimize launch strategies by improving prescriber targeting, detecting market-access risks, segmenting patient and payer profiles, and enabling real-time decision-making.

Results: The findings indicate that the models decrease forecast variance, improve prescriber reach, and enable earlier corrective interventions during the early launch stage. The models support managerial decision-making by scoring prescriber adoption propensity and categorizing market-access risks to streamline payer strategies.

Conclusion: The study demonstrates that integrating predictive classification models into ERP-based pharmaceutical workflows enhances agility and supports more evidence-based, accurate, and timely decision-making, thereby improving overall launch performance.

Recommendation: The study highlights the need to integrate supervised machine-learning models into pharmaceutical launch workflows while emphasizing the importance of governance systems, privacy, equity, and regulatory considerations to enable proactive changes, improve market accessibility, and optimize resource allocation.