search for




 

A study on initial price change prediction of IPO shares using non-financial information
Journal of the Korean Data & Information Science Society 2018;29:425-39
Published online March 31, 2018
© 2018 Korean Data and Information Science Society.

Sanghun Shin1 · Hyun Jun Lee2 · Jae Joon Ahn3

1Department of Investment Information Engineering, Yonsei University
2Department of Industrial Engineering, Yonsei University
3Department of Information & Statistics, Yonsei University
Correspondence to: Assistant professor, Department of Information & Statistics, Yonsei University, Wonju 26493, Korea. E-mail: ahn2615@yonsei.ac.kr
Received February 17, 2018; Revised March 16, 2018; Accepted March 16, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The stock in a public offering refers to stocks that are sold to an unspecified public to be listed on the KOSPI or the KOSDAQ market. Because the initial public offering (IPO)’s closing price of offering day mostly tends to rise opposed to the offering price of it, which is selling price, it is a good alternative investment asset in the low interest rate period. However, it is difficult for individual investors to obtain and analyze information on public offerings and IPO stocks compared to institutional investors. Therefore, this paper confirms whether individual investors can predict the rise and fall of the IPO’s closing price of offering day compared to its offering price by using multiple data analysis methodologies and non-financial data that is relatively easy to collect, and compares the accuracy of them. Logistic regression, discriminant analysis, decision tree, artificial neural network, case based reasoning, and support vector machine were used for analysis, and the empirical experiments was conducted using the IPO data from 2007 to September 6, 2017.
Keywords : Artificial neural network, initial public offering (IPO), logistic regression, stock in a public offering, support vector machine.