An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings
Due to their aptitude in both accurate data processing and human comprehensible reasoning, neural fuzzy inference systems have been widely adopted in various application domains as decision support systems. Especially in real-world scenarios such as decision making in financial transactions, the hum...
Saved in:
Main Authors: | , , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2018
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/80561 http://hdl.handle.net/10220/46696 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-80561 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-805612020-03-07T11:48:52Z An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings Qian, Xiaolin Quek, Chai Miao, Chunyan Wang, Di Zhang, Xiaofeng Ng, Geok See Zhou, You Tan, Ah-Hwee School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering Neural Fuzzy Inference System Interpretable Rules Due to their aptitude in both accurate data processing and human comprehensible reasoning, neural fuzzy inference systems have been widely adopted in various application domains as decision support systems. Especially in real-world scenarios such as decision making in financial transactions, the human experts may be more interested in knowing the comprehensive reasons of certain advices provided by a decision support system in addition to how confident the system is on such advices. In this paper, we apply an integrated autonomous computational model termed genetic algorithm and rough set incorporated neural fuzzy inference system (GARSINFIS) to predict underpricing in initial public offerings (IPOs). The difference between a stock’s potentially high value and its actual IPO price is referred as money-left-on-the-table, which has been extensively studied in the literature of corporate finance on its theoretical foundations, but surprisingly under-investigated in the field of computational decision support systems. Specifically, we use GARSINFIS to derive interpretable rules in determining whether there is money-left-on-the-table in IPOs to assist the investors in their decision making. For performance evaluations, we first demonstrate how to balance between accuracy and interpretability in GARSINFIS by simply altering the values of several coefficient parameters using well-known datasets. We then use GARSINFIS to investigate the IPO underpricing problem. The encouraging experimental results show that we may yield higher initial returns of IPOs by following the advices provided by GARSINFIS than any other benchmarking model. Therefore, our autonomous computational model is shown to be capable of offering the investors highly interpretable and reliable decision supports to grab the money-left-on-the-table in IPOs. NRF (Natl Research Foundation, S’pore) Accepted version 2018-11-23T05:27:52Z 2019-12-06T13:52:15Z 2018-11-23T05:27:52Z 2019-12-06T13:52:15Z 2018 2018 Journal Article Wang, D., Qian, X., Quek, C., Tan, A. H., Miao, C., Zhang, X., ... Zhou, Y. (2018). An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings. Neurocomputing, 319102-117. doi:10.1016/j.neucom.2018.07.036 0925-2312 https://hdl.handle.net/10356/80561 http://hdl.handle.net/10220/46696 10.1016/j.neucom.2018.07.036 209068 en Neurocomputing © 2018 Elsevier. This is the author created version of a work that has been peer reviewed and accepted for publication by Neurocomputing, Elsevier. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [https://doi.org/10.1016/j.neucom.2018.07.036]. 49 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Computer science and engineering Neural Fuzzy Inference System Interpretable Rules |
spellingShingle |
DRNTU::Engineering::Computer science and engineering Neural Fuzzy Inference System Interpretable Rules Qian, Xiaolin Quek, Chai Miao, Chunyan Wang, Di Zhang, Xiaofeng Ng, Geok See Zhou, You Tan, Ah-Hwee An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings |
description |
Due to their aptitude in both accurate data processing and human comprehensible reasoning, neural fuzzy inference systems have been widely adopted in various application domains as decision support systems. Especially in real-world scenarios such as decision making in financial transactions, the human experts may be more interested in knowing the comprehensive reasons of certain advices provided by a decision support system in addition to how confident the system is on such advices. In this paper, we apply an integrated autonomous computational model termed genetic algorithm and rough set incorporated neural fuzzy inference system (GARSINFIS) to predict underpricing in initial public offerings (IPOs). The difference between a stock’s potentially high value and its actual IPO price is referred as money-left-on-the-table, which has been extensively studied in the literature of corporate finance on its theoretical foundations, but surprisingly under-investigated in the field of computational decision support systems. Specifically, we use GARSINFIS to derive interpretable rules in determining whether there is money-left-on-the-table in IPOs to assist the investors in their decision making. For performance evaluations, we first demonstrate how to balance between accuracy and interpretability in GARSINFIS by simply altering the values of several coefficient parameters using well-known datasets. We then use GARSINFIS to investigate the IPO underpricing problem. The encouraging experimental results show that we may yield higher initial returns of IPOs by following the advices provided by GARSINFIS than any other benchmarking model. Therefore, our autonomous computational model is shown to be capable of offering the investors highly interpretable and reliable decision supports to grab the money-left-on-the-table in IPOs. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Qian, Xiaolin Quek, Chai Miao, Chunyan Wang, Di Zhang, Xiaofeng Ng, Geok See Zhou, You Tan, Ah-Hwee |
format |
Article |
author |
Qian, Xiaolin Quek, Chai Miao, Chunyan Wang, Di Zhang, Xiaofeng Ng, Geok See Zhou, You Tan, Ah-Hwee |
author_sort |
Qian, Xiaolin |
title |
An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings |
title_short |
An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings |
title_full |
An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings |
title_fullStr |
An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings |
title_full_unstemmed |
An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings |
title_sort |
interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings |
publishDate |
2018 |
url |
https://hdl.handle.net/10356/80561 http://hdl.handle.net/10220/46696 |
_version_ |
1681046800299982848 |