{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:56:18Z","timestamp":1762343778147,"version":"build-2065373602"},"reference-count":0,"publisher":"SASA Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JISIS"],"published-print":{"date-parts":[[2025,8,30]]},"abstract":"<jats:p>Data from the financial cloud network monitoring is dispersed and Innovative. There can be \nintermittent appearances of signals to monitor the cloud or vary in significance and clearness. As a \nresult, machine learning (ML) techniques that are adjusted to a particular data set cannot be sufficient \nfor very long. A model's accuracy can decrease as a result of changes in the qualities and input data \nthroughout time. For this reason, it is frequently necessary to use distributed learning with creative \nmodel selection. However, there are several drawbacks to ensemble machine learning. These include \nthe necessity of constant training, the need for high amounts of processing power and big training \ndatasets, the significant danger of over fitting along with the lengthy and laborious process of \ndeveloping a model. In this research, offer a unique cloud methodology that is competitive using the \nmethods used today for automatically choosing and fine-tuning ML models. Our approach \nautomates the process of selecting and developing the model. Before the automatic construction of \nfocused supervised learning models of Support Vector Machine (SVM) and Extreme Gradient Boost \n(XG Boost), leverage unsupervised learning models of K-means Clustering and singular Value \nDecomposition to more thoroughly investigate the data domain. Specifically, research utilize an \ninnovative autoscaling method to build and assess ML algorithm instances dynamically and with the \nhelp of messages between instances and container orchestration, research present a Cloud ML framework for autotuning and selection. Datasets related to financial cloud security for finance are \nused to illustrate the suggested technique and tool.<\/jats:p>","DOI":"10.58346\/jisis.2025.i3.042","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:51:11Z","timestamp":1762343471000},"page":"626-638","source":"Crossref","is-referenced-by-count":0,"title":["An Innovative AI-driven Autotuning and Autoselection for  Intelligent Financial Cloud Security"],"prefix":"10.58346","volume":"15","author":[{"given":"Dr. Trupti","family":"Manish Rathi","sequence":"first","affiliation":[]},{"given":"Dr. Ashutosh","family":"Panchbhai","sequence":"additional","affiliation":[]},{"given":"Dr. Arvind Kumar","family":"Pandey","sequence":"additional","affiliation":[]},{"given":"Kshipra","family":"Jain","sequence":"additional","affiliation":[]},{"given":"R. Hannah","family":"Jessie Rani","sequence":"additional","affiliation":[]},{"given":"Dr. Anita","family":"Sable","sequence":"additional","affiliation":[]}],"member":"37075","published-online":{"date-parts":[[2025,8,30]]},"container-title":["Journal of Internet Services and Information Security"],"original-title":[],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:51:17Z","timestamp":1762343477000},"score":1,"resource":{"primary":{"URL":"https:\/\/jisis.org\/wp-content\/uploads\/2025\/11\/2025.I3.042.pdf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,30]]},"references-count":0,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,8,30]]},"published-print":{"date-parts":[[2025,8,30]]}},"URL":"https:\/\/doi.org\/10.58346\/jisis.2025.i3.042","relation":{},"ISSN":["2182-2069","2182-2077"],"issn-type":[{"type":"print","value":"2182-2069"},{"type":"electronic","value":"2182-2077"}],"subject":[],"published":{"date-parts":[[2025,8,30]]}}}