From Batch to Event Streams: Real-Time Cost and Inventory Forecasting Using Event-Driven Architectures Jaya Ram Menda

Jaya Ram Menda

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2023, vol. 9, issue 9, 178-189

Abstract: Modern enterprises operating in retail, manufacturing, and supply chain domains face increasing pressure to forecast inventory levels and operational costs with minimal latency as globalized markets, omnichannel commerce, and increasingly volatile demand patterns reduce the effectiveness of static planning cycles. Traditional batch-oriented forecasting systems, while statistically robust and well suited for historical analysis, often fail to respond adequately to rapidly changing demand signals, supply disruptions, logistics constraints, and pricing volatility because they rely on delayed data aggregation and periodic recomputation. This paper proposes an architectural approach for real-time cost and inventory forecasting using event-driven architectures (EDA), in which business-relevant events such as sales transactions, inventory movements, supplier updates, and cost changes are continuously captured and processed as immutable streams. By combining event streaming platforms with continuous forecasting models, organizations can move from reactive, retrospective planning toward proactive, real-time decision-making that supports dynamic replenishment, pricing, and cost control. The paper synthesizes prior work in event-driven systems, stream processing, and demand forecasting to demonstrate how architectural latency, data freshness, and computational responsiveness are as critical as model accuracy, and presents a reference architecture that enables low-latency, scalable, and resilient forecasting pipelines suitable for modern enterprise environments.

Keywords: Event-Driven Architecture; Real-Time Forecasting; Inventory Management; Cost Optimization; Event Streaming; Apache Kafka; Demand Forecasting; Supply Chain Analytics; Stream Processing; CQRS (search for similar items in EconPapers)
Date: 2023
Note: Article URL: https://ijsrcseit.com/CSEIT239927
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrcseit.com/CSEIT239927 Article URL (text/html)
https://ijsrcseit.com/paper/CSEIT239927.pdf Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:jbh:ijsrcs:v9:y2023:i9:id:hcseit239927

DOI: 10.32628/CSEIT239927

Access Statistics for this article

More articles in International Journal of Scientific Research in Computer Science, Engineering and Information Technology from International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Bibliographic data for series maintained by Pankaj Sharma (USA) ().