Introduction to the Minitrack on Machine Learning and Predictive Analytics in Accounting, Finance and Management

Peter Sarlin, Jozsef Mezei

Research output: Chapter in Book/Conference proceedingConference contributionScientificpeer-review

Abstract

The use of advanced statistical models, predictive
analytics and machine learning have been present in
the fields of accounting, finance and management for
several decades. However, recent years have seen an
ever increasingly growing trend of utilizing these
approaches, as a result of the rapid evolution of related
technologies mathematical algorithms. These
developments include, but are not limited to: (i) the
widespread availability of large amount of data,
specifically data streams in new domains, (ii) the
commoditization of advanced machine learning (ML)
and artificial intelligence (AI) algorithms, such as deep
learning in open source programming packages, (iii)
the decrease in costs and complexity of performing
computationally extensive modelling. These trends are
observable in both academia and industry: for
organizations, using AI and ML is not a source of
competitive advantage anymore, but rather a necessity
to remain profitable. The minitrack aims at showcasing
some of the most interesting application domains and
novel machine learning techniques applied to both
structured and unstructured data sources.
Original languageEnglish
Title of host publicationProceedings of the 53rd Hawaii International Conference on System Sciences
Publication statusPublished - 2020
MoE publication typeA4 Article in a conference publication
EventHAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCES - Hawaii International Conference on System Sciences
Duration: 7 Jan 202010 Jan 2020

Conference

ConferenceHAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCES
Period07/01/2010/01/20

Fingerprint Dive into the research topics of 'Introduction to the Minitrack on Machine Learning and Predictive Analytics in Accounting, Finance and Management'. Together they form a unique fingerprint.

Cite this