Quotation Baughman, Matt, Haas, Christian, Wolski, Rich, Foster, Ian, Chard, Kyle. 2018. Predicting Amazon Spot Prices with LSTM Networks. In Proceedings of the 9th Workshop on Scientific Cloud Computing, Hrsg. ScienceCloud 2018, 1-7. New York, New York, USA: None.




Amazon spot instances provide preemptable computing capacity at a cost that is often significantly lower than comparable on-demand or reserved instances. Spot instances are charged at the current spot price: a fluctuating market price based on supply and demand for spot instance capacity. However, spot instances are inherently volatile, the spot price changes over time, and instances can be revoked by Amazon with as little as two minutes' warning. Given the potential discount---up to 90% in some cases---there has been significant interest in the scientific cloud computing community to leverage spot instances for workloads that are either fault-tolerant or not time-sensitive. However, cost-effective use of spot instances requires accurate prediction of spot prices in the future. We explore here the use of long/short-term memory (LSTM) recurrent neural networks for spot price prediction. We describe our model and compare it against a baseline ARIMA model using historical spot pricing data. Our results show that our LSTM approach can reduce training error by as much as 95%.


Press 'enter' for creating the tag

Publication's profile

Status of publication Published
Affiliation External
Type of publication Contribution to conference proceedings
Language English
Title Predicting Amazon Spot Prices with LSTM Networks
Title of whole publication Proceedings of the 9th Workshop on Scientific Cloud Computing
Editor ScienceCloud 2018
Page from 1
Page to 7
Location New York, New York, USA
Year 2018
ISBN 9781450358637
URL http://dl.acm.org/citation.cfm?doid=3217880.3217881
Open Access N


Haas, Christian (Details)
Baughman, Matt (University of Chicago, United States/USA)
Chard, Kyle (University of Chicago, United States/USA)
Foster, Ian (University of Chicago, United States/USA)
Wolski, Rich (University of California - Santa Barbara, United States/USA)
Google Scholar: Search