Join query optimization is a complex task and is central to the performance of query processing. In fact it belongs to the class of NP-hard problems. Traditional query optimizers use dynamic programming (DP) methods combined with a set of rules and restrictions to avoid exhaustive enumeration of all possible join orders. However, DP methods are very resource intensive. Moreover, given simplifying assumptions of attribute independence, traditional query optimizers rely on erroneous cost estimations, which can lead to suboptimal query plans.Recent success of deep reinforcement learning (DRL) creates new opportunities for the field of query optimization to tackle the above-mentioned problems. In this paper, we present our DRL-based Fully Observed Optimizer (FOOP) which is a generic query optimization framework that enables plugging in different machine learning algorithms. The main idea of FOOP is to use a data-adaptive learning query optimizer that avoids exhaustive enumerations of join orders and is thus significantly faster than traditional approaches based on dynamic programming. In particular, we evaluate various DRL-algorithms and show that Proximal Policy Optimization significantly outperforms Q-learning based algorithms. Finally we demonstrate how ensemble learning techniques combined with DRL can further improve the query optimizer.
Today, nearly all money exists in form of numbers in a computer, and finance can be considered as a special kind of IT application that represents the flow of money in form of cash flows between different participants. Thus, automated processing seems to be a natural choice and the financial sector should be expected to lead digitization and automation initiatives. It is all the more surprising that not only is this not the case but, on the contrary, the financial sector is lagging behind other sectors. In 2008, when Lehman Brothers went bankrupt at the height of the financial crisis, nobody-neither the big banks nor the regulatory authorities-had the structures and processes in place to systematically measure, even imprecisely, the systemic aspects of the risks inherent in the development of subprime lending, securitization, and risk transfer [1]. As a consequence, the top management did not have an adequate picture of these risks so that they could be denied during the build-up of the bubble and nobody was able to evaluate the implications of the failure of major financial institutions when the crisis eventually hit. The major shortcoming identified by the Basel Committee on Banking Supervision
Real-time financial risk analytics is very challenging due to heterogeneous data sets within and across banks worldwide and highly volatile financial markets. Moreover, large financial organizations have hundreds of millions of financial contracts on their balance sheets. Since there is no standard for modelling financial data, current financial risk algorithms are typically inconsistent and non-scalable. In this paper, we present a novel implementation of a real-world use case for performing largescale financial risk analytics leveraging Big Data technology. Our performance evaluation demonstrates almost linear scalability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.