Econometric: Modification Technique of Fuzzy Time Series First Order and Time-Invariant Chen and Hsu To Increase The Forecasting Accuracy of Value Stock Index in Indonesia

Zulfikar, Rizka and Mayvita, Prihatini Ade and Purboyo, Purboyo (2019) Econometric: Modification Technique of Fuzzy Time Series First Order and Time-Invariant Chen and Hsu To Increase The Forecasting Accuracy of Value Stock Index in Indonesia. In: The First Borneo International Conference For Education And Social Science (BICESS), September, 10, 2018, Banjarmasin. (Submitted)

[img] Text
full_paper_abs-37_1911171519.docx - Accepted Version

Download (99kB)

Abstract

This econometric research aims to develop the fuzzy time series - Chen and Hsu first order and time-invariant for forecasting the value of stocks. Process modifications made to the methods of fuzzy time series - Chen and Hsu because there are still some significant fluctuation variances in some period of data and trend predictions do not fully follow the actual trend of the stock price movement. The modifications had conducted at the redivided interval step and assuming that all group intervals data have the same opportunity to improve the accuracy of forecasting. The data used in this research are the index of Jakarta Stock Exchange (JSX) and index of LQ-45 from July to August 2017. The results of this research have found that the modification of fuzzy time series at intervals redivided step able to provide better forecasting accuracy. Keywords: Stocks Forecasting, Fuzzy Time Series, Chen and Hsu, First Order And Time Invariant.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Stocks Forecasting, Fuzzy Time Series, Chen and Hsu, First Order And Time Invariant.
Subjects: H Social Sciences > H Social Sciences (General)
H Social Sciences > HB Economic Theory
Divisions: Faculty of Law, Arts and Social Sciences > School of Management
Depositing User: Rizka Zulfikar
Date Deposited: 20 Dec 2019 01:01
Last Modified: 25 Oct 2023 06:08
URI: http://eprints.uniska-bjm.ac.id/id/eprint/38

Actions (login required)

View Item View Item