Ekpenyong, Francis, Samakovitis, Georgios ORCID: https://orcid.org/0000-0002-0076-8082, Kapetanakis, Stelios and Petridis, Miltos (2019) An Ensemble Method: Case-Based Reasoning and the Inverse Problems in Investigating Financial Bubbles. In: Cognitive Computing – ICCC 2019. Lecture Notes in Computer Science, 11518 . Springer, Switzerland, pp. 153-168. ISBN 978-3030234065 ISSN 0302-9743 (Print), 1611-3349 (Online) (doi:10.1007/978-3-030-23407-2_13)

Preview

PDF (Author's Accepted Manuscript) 24677 SAMAKOVITIS_Ensemble_Method_Inverse_Problems_(AAM)_2019.pdf - Accepted Version Download (450kB) | Preview

Abstract

This paper presents an ensemble approach and model; IPCBR, that leverages the capabilities of Case based Reasoning (CBR) and Inverse Problem Techniques (IPTs) to describe and model abnormal stock market fluctuations (often associated with asset bubbles) in time series datasets from historical stock market prices. The framework proposes to use a rich set of past observations and geometric pattern description and then applies a CBR to formulate the forward problem; Inverse Problem formulation is then applied to identify a set of parameters that can statistically be associated with the occurrence of the observed patterns. The technique brings a novel perspective to the problem of asset bubbles predictability. Conventional research practice uses traditional forward approaches to predict abnormal fluctuations in financial time series; conversely, this work proposes a formative strategy aimed to determine the causes of behaviour, rather than predict future time series points. This suggests a deviation from the existing research trend.

Item Type:	Conference Proceedings
Title of Proceedings:	Cognitive Computing – ICCC 2019
Additional Information:	This paper won an award at the ICCC 2019 conference.
Uncontrolled Keywords:	Case-based reasoning, inverse problems, asset bubble, machine learning, time series
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS) Faculty of Engineering & Science
Last Modified:	04 Mar 2022 13:06
URI:	http://gala.gre.ac.uk/id/eprint/24677

Actions (login required)

View Item

Downloads