EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cloud-Native Scalable Learning-to-Rank Architecture for Real-Time Search Optimization

Saraschandra Arveti, Anish Hadkar, Mani Teja Nutalapati

International Journal of Computational and Experimental Science and Engineering · 30.12.2025 · 11 (4)

DOI: 10.22399/ijcesen.5118 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computational and Experimental Science and Engineering, online erschienen am 30.12.2025. Verfasst von Saraschandra Arveti und 2 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Today, search engines must be capable of delivering extremely relevant results while handling a large number of queries simultaneously in real time. A cloud-native, scalable Learning to Rank (LTR) system can leverage distributed computing, microservices, and on-demand cloud resources for the efficient search optimization task. This approach will incorporate machine learning based ranking models into the search pipeline, thereby enabling the system to re-evaluate and re-order the results in line with user intent, contextual signals, and historical interaction data in a dynamic manner. The proposed architecture utilizes containerized services, stream processing, and scalable storage for real, time feature extraction, model inference, and continuous model updates. By making use of orchestration platforms and serverless components, the system can automatically scale without any human intervention even when workload fluctuations are extreme. It will also maintain low latency and high availability. Data pipelines collect clickstream and behavioral data which are then used to train and periodically retrain the LTR models so that the ranking strategies always reflect the changing preferences of the users. Besides, the design includes facilities for A/B testing, monitoring, and model versioning which give a way to controlled experimentation and performance optimization. Using caching layers and distributed indexing mechanisms results in improved response times and reduced computational overhead.

Zitieren

APA

Arveti, S., Hadkar, A., & Nutalapati, M. T. (2025). Cloud-Native Scalable Learning-to-Rank Architecture for Real-Time Search Optimization. International Journal of Computational and Experimental Science and Engineering, 11(4). https://doi.org/10.22399/ijcesen.5118

Vancouver

Arveti S, Hadkar A, Nutalapati MT. Cloud-Native Scalable Learning-to-Rank Architecture for Real-Time Search Optimization. International Journal of Computational and Experimental Science and Engineering. 2025;11(4). doi:10.22399/ijcesen.5118

BibTeX
@article{Arveti2025,
  author = {Arveti, Saraschandra and Hadkar, Anish and Nutalapati, Mani Teja},
  title = {Cloud-Native Scalable Learning-to-Rank Architecture for Real-Time Search Optimization},
  journal = {International Journal of Computational and Experimental Science and Engineering},
  year = {2025},
  volume = {11},
  number = {4},
  doi = {10.22399/ijcesen.5118}
}
Kostenlos starten →