Home // ICSEA 2023, The Eighteenth International Conference on Software Engineering Advances // View article
Authors:
Domingos Monteiro
Felipe Ferraz
Silvio Meira
Domingos Salazar
Keywords: Big Data; Data Value; Big Data Monetization; Artificial Intelligence; Game Theory; Information Theory; Shapley Value; Digital Assets
Abstract:
Despite significant research on data monetization in recent years, the academic literature lacks universally applicable methods for this endeavor. This study seeks to introduce a versatile method suitable for various databases and prevalent challenges in both academic and commercial realms. Our methodology draws from information theory and game theory, leveraging the Return On Investment (ROI) metric as a value determinant. The derived method calculates the ROI contributed by distinct databases for binary decision-making, incorporating the Shapley Value concept from cooperative game theory. We tested this method on a practical dilemma— underwriting car insurance policies in Brazil. Our method adeptly pinpointed the financial contribution of each dataset to the assessed decisions. It can be adapted for other binary decision contexts where financial outcomes of decisions are either provided or quantifiable. Given the novelty of this research domain, we anticipate this study to spur further exploration into data valuation in the realm of data science and Big Data.
Pages: 64 to 74
Copyright: Copyright (c) IARIA, 2023
Publication date: November 13, 2023
Published in: conference
ISSN: 2308-4235
ISBN: 978-1-68558-098-8
Location: Valencia, Spain
Dates: from November 13, 2023 to November 17, 2023