{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:15:03Z","timestamp":1783610103849,"version":"3.55.0"},"reference-count":44,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003447","name":"State Scholarships Foundation Greece (IKY)","doi-asserted-by":"publisher","award":["2022-050-0502-52245"],"award-info":[{"award-number":["2022-050-0502-52245"]}],"id":[{"id":"10.13039\/501100003447","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>When exploring alternative cloud solution designs, it is important to also consider cost. Thus, having a comprehensive view of the cloud market and future price evolution allows well-informed decisions to choose between alternatives. Cloud providers offer various service types with different pricing policies. Currently, infrastructure-as-a-Service (IaaS) is considered the most mature cloud service, while reserved instances, where virtual machines are reserved for a fixed period of time, have the largest market share. In this work, we employ a machine-learning approach based on the CatBoost algorithm to explore a price-prediction model for the reserve instance market. The analysis is based on historical data provided by Amazon Web Services from 2016 to 2022. Early results demonstrate the machine-learning model\u2019s ability to capture the underlying evolution patterns and predict future trends. Findings suggest that prediction accuracy is not improved by integrating data from older time periods.<\/jats:p>","DOI":"10.3390\/fi15080277","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T01:38:31Z","timestamp":1692581911000},"page":"277","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Applying Machine Learning in Cloud Service Price Prediction: The Case of Amazon IaaS"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3418-6443","authenticated-orcid":false,"given":"George","family":"Fragiadakis","sequence":"first","affiliation":[{"name":"Department of Informatics and Telematics, Harokopio University of Athens, 17671 Kallithea, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2791-2582","authenticated-orcid":false,"given":"Evangelia","family":"Filiopoulou","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telematics, Harokopio University of Athens, 17671 Kallithea, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4401-5058","authenticated-orcid":false,"given":"Christos","family":"Michalakelis","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telematics, Harokopio University of Athens, 17671 Kallithea, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-1438","authenticated-orcid":false,"given":"Thomas","family":"Kamalakis","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telematics, Harokopio University of Athens, 17671 Kallithea, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4541-961X","authenticated-orcid":false,"given":"Mara","family":"Nikolaidou","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telematics, Harokopio University of Athens, 17671 Kallithea, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/MIC.2016.4","article-title":"Pricing the cloud","volume":"20","author":"Kash","year":"2016","journal-title":"IEEE Internet Comput."},{"key":"ref_2","first-page":"2","article-title":"Pricing schemes in cloud computing: An overview","volume":"7","author":"Mazrekaj","year":"2016","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_3","unstructured":"(2023, April 20). Gartner. Available online: https:\/\/www.gartner.com\/en\/newsroom\/press-releases\/2022-10-31-gartner-forecasts-worldwide-public-cloud-end-user-spending-to-reach-nearly-600-billion-in-2023."},{"key":"ref_4","unstructured":"Amazon (2023, April 25). Amazon EC2. Available online: https:\/\/aws.amazon.com\/ec2\/."},{"key":"ref_5","unstructured":"Statista (2023, June 30). Infrastructure As a Service (IaaS) Software Market Share Worldwide 2022, by Vendor. Available online: https:\/\/www.statista.com\/statistics\/1258463\/infrastructure-as-a-service-software-market-share-vendor-worldwide\/."},{"key":"ref_6","unstructured":"Amazon (2023, May 25). Amazon Elastic Container Service. Available online: https:\/\/aws.amazon.com\/ecs\/."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.future.2019.01.025","article-title":"Reducing the price of resource provisioning using EC2 spot instances with prediction models","volume":"96","author":"Fabra","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_8","first-page":"8","article-title":"AWS EC2 instance spot price forecasting using LSTM networks","volume":"2","author":"Lancon","year":"2019","journal-title":"SMU Data Sci. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e4451","DOI":"10.1002\/cpe.4451","article-title":"Statistical analysis of Amazon EC2 cloud pricing models","volume":"31","author":"Portella","year":"2019","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/TCC.2017.2780159","article-title":"Amazon EC2 spot price prediction using regression random forests","volume":"8","author":"Khandelwal","year":"2017","journal-title":"IEEE Trans. Cloud Comput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1186\/s13673-020-00239-5","article-title":"Cloud spot instance price prediction using kNN regression","volume":"10","author":"Liu","year":"2020","journal-title":"Hum.-Centric Comput. Inf. Sci."},{"key":"ref_12","first-page":"65","article-title":"AWS PredSpot: Machine Learning for Predicting the Price of Spot Instances in AWS Cloud","volume":"7","author":"Saez","year":"2022","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7626","DOI":"10.1007\/s11227-022-04970-x","article-title":"Optimal prediction of cloud spot instance price utilizing deep learning","volume":"79","author":"Nezamdoust","year":"2023","journal-title":"J. Supercomput."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/S0969-6989(00)00011-4","article-title":"Forecasting aggregate retail sales: A comparison of artificial neural networks and traditional methods","volume":"8","author":"Alon","year":"2001","journal-title":"J. Retail. Consum. Serv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"106380","DOI":"10.1016\/j.cie.2020.106380","article-title":"Demand forecasting in supply chain: The impact of demand volatility in the presence of promotion","volume":"142","author":"Abolghasemi","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.procs.2022.12.115","article-title":"Machine learning approaches in stock market prediction: A systematic literature review","volume":"216","author":"Mintarya","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Mudassir, M., Bennbaia, S., Unal, D., and Hammoudeh, M. (2020). Time-series forecasting of Bitcoin prices using high-dimensional features: A machine learning approach. Neural Comput. Appl.","DOI":"10.1007\/s00521-020-05129-6"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/OAJPE.2020.3029979","article-title":"Energy forecasting: A review and outlook","volume":"7","author":"Hong","year":"2020","journal-title":"IEEE Open Access J. Power Energy"},{"key":"ref_19","unstructured":"Nashold, L., and Krishnan, R. (2020). Using LSTM and SARIMA models to forecast cluster CPU usage. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/TCC.2018.2858266","article-title":"Hedonic pricing of cloud computing services","volume":"9","author":"Wu","year":"2018","journal-title":"IEEE Trans. Cloud Comput."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Alkharif, S., Lee, K., and Kim, H. (2017, January 7\u20139). Time-series analysis for price prediction of opportunistic cloud computing resources. Proceedings of the 7th International Conference on Emerging Databases: Technologies, Applications, and Theory, Busan, Republic of Korea.","DOI":"10.1007\/978-981-10-6520-0_23"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3499","DOI":"10.1007\/s10586-022-03581-8","article-title":"An exploration to graphics processing unit spot price prediction","volume":"25","author":"Khan","year":"2022","journal-title":"Clust. Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e3731","DOI":"10.1002\/ett.3731","article-title":"Cloud traffic prediction based on fuzzy ARIMA model with low dependence on historical data","volume":"33","author":"Mehdi","year":"2022","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"200971","DOI":"10.1109\/ACCESS.2020.3035328","article-title":"Electricity Price Forecasting for Cloud Computing Using an Enhanced Machine Learning Model","volume":"8","author":"Albahli","year":"2020","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/s00607-022-01129-7","article-title":"Time series-based workload prediction using the statistical hybrid model for the cloud environment","volume":"105","author":"Devi","year":"2023","journal-title":"Computing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/s10723-021-09561-3","article-title":"Cloud resource demand prediction using machine learning in the context of qos parameters","volume":"19","author":"Nawrocki","year":"2021","journal-title":"J. Grid Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1080\/01605682.2020.1843976","article-title":"A hybrid model based on bidirectional long short-term memory neural network and Catboost for short-term electricity spot price forecasting","volume":"73","author":"Zhang","year":"2022","journal-title":"J. Oper. Res. Soc."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"113511","DOI":"10.1016\/j.jenvman.2021.113511","article-title":"The effect of green energy, global environmental indexes, and stock markets in predicting oil price crashes: Evidence from explainable machine learning","volume":"298","author":"Jabeur","year":"2021","journal-title":"J. Environ. Manag."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"114261","DOI":"10.1016\/j.psychres.2021.114261","article-title":"Using CatBoost algorithm to identify middle-aged and elderly depression, national health and nutrition examination survey 2011\u20132018","volume":"306","author":"Zhang","year":"2021","journal-title":"Psychiatry Res."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Pandey, S., and Lahoti, S. (2023, January 24\u201325). Intrusion Detection System Analysis Using Cat boost Technique Intended for Cloud Communication Network. Proceedings of the 2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS), Raichur, India.","DOI":"10.1109\/ICICACS57338.2023.10099596"},{"key":"ref_31","unstructured":"Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv."},{"key":"ref_32","unstructured":"Amazon (2023, May 25). Scale Your Machine Learning Workloads on Amazon ECS Powered by AWS Trainium Instances. Available online: https:\/\/aws.amazon.com\/blogs\/machine-learning\/scale-your-machine-learning-workloads-on-amazon-ecs-powered-by-aws-trainium-instances\/."},{"key":"ref_33","first-page":"20","article-title":"Big Data Analytics and Modelling","volume":"843","author":"Gaffoor","year":"2021","journal-title":"J. Softw. Eng. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1016\/S0895-7177(01)00109-1","article-title":"The mean and median absolute deviations","volume":"34","author":"Hung","year":"2001","journal-title":"Math. Comput. Model."},{"key":"ref_35","first-page":"6","article-title":"Comparison between XGBoost, LightGBM and CatBoost using a home credit dataset","volume":"13","year":"2019","journal-title":"Int. J. Comput. Inf. Eng."},{"key":"ref_36","unstructured":"Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R. (2018, January 3\u20138). CatBoost: Unbiased boosting with categorical features. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/s40537-020-00369-8","article-title":"CatBoost for big data: An interdisciplinary review","volume":"7","author":"Hancock","year":"2020","journal-title":"J. Big Data"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"102441","DOI":"10.1016\/j.simpat.2021.102441","article-title":"A pricing model for Container-as-a-Service, based on hedonic indices","volume":"115","author":"Liagkou","year":"2022","journal-title":"Simul. Model. Pract. Theory"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Fragiadakis, G., Liagkou, V., Filiopoulou, E., Fragkakis, D., Michalakelis, C., and Nikolaidou, M. (2023). Cloud services cost comparison: A clustering analysis framework. Computing, 1\u201328.","DOI":"10.1007\/s00607-023-01173-x"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1080\/00031305.1988.10475530","article-title":"Maximum Z Scores and Outliers","volume":"42","author":"Shiffler","year":"1988","journal-title":"Am. Stat."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Chun, S.H. (2019). Cloud services and pricing strategies for sustainable business models: Analytical and numerical approaches. Sustainability, 12.","DOI":"10.3390\/su12010049"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1080\/07474938.2010.481556","article-title":"An empirical comparison of machine learning models for time series forecasting","volume":"29","author":"Ahmed","year":"2010","journal-title":"Econom. Rev."},{"key":"ref_43","unstructured":"Prado, R., and West, M. (2010). Time Series: Modeling, Computation, and Inference, Chapman and Hall\/CRC."},{"key":"ref_44","unstructured":"Hyndman, R.J., and Athanasopoulos, G. (2018). Forecasting: Principles and Practice, OTexts."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/15\/8\/277\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:37:34Z","timestamp":1760128654000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/15\/8\/277"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,19]]},"references-count":44,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["fi15080277"],"URL":"https:\/\/doi.org\/10.3390\/fi15080277","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,19]]}}}