Forecasting inflation rate in Malaysia using Artificial Neural Network (ANN) Approach / Muhammad Athir Mohd Junaidi and Siti Aishah Mohd Shafie

Mohd Junaidi, Muhammad Athir and Mohd Shafie, Siti Aishah (2023) Forecasting inflation rate in Malaysia using Artificial Neural Network (ANN) Approach / Muhammad Athir Mohd Junaidi and Siti Aishah Mohd Shafie. In: International Jasin Multimedia & Computer Science Invention and Innovation Exhibition (i-JaMCSIIX 2023). Faculty of Computer and Mathematical Sciences, Kampus Jasin, p. 42. (Submitted)

Abstract

Forecasting is very important for planning and decision-making in all fields to predict the conditions and cases surrounding the problem under study before making any decision. Hence, many forecasting methods have been developed to produce accurate predicted values. Inflation rates provide appropriate and timely information about the trend changes, which affect the economy of Malaysia because of the different uses in many ways. It can be used as an economic indicator that is beneficial for policy makers, investors, and consumers to make a planning and decision. It also used as a supplement for statistical chains to predict future values rate to make sure that the data accurately reflect the pattern of the inflation rate in Malaysia. Therefore, the main objective of this study is to construct an inflation rate model for Malaysia and make a prediction of inflation rate for upcoming six months in 2023 by using artificial neural network (ANN). The proposed ANN model consists of an input layer, hidden layer, and output layer, while it applies the tangent function (TanH) as a testing and validation algorithm in the hidden layer. Finally, the predicted values of inflation rate are compared with the measured values. The proposed ANN model with four hidden nodes is more efficient than other models in predicting inflation rate after considering parsimonious architecture. The obtained Coefficient of Determination and Root Mean Squared Error (RMSE) values using the ANN method is 0.6399 and 0.9879 respectively. This study presents a new model for forecasting inflation rate values that are beneficial for many parties. The model was used to predict upcoming months then compared to the actual data.

Metadata

Item Type: Book Section
Creators:
Creators
Email / ID Num.
Mohd Junaidi, Muhammad Athir
athirjunaidi29@gmail.com
Mohd Shafie, Siti Aishah
ctaishah@uitm.edu.my
Contributors:
Contribution
Name
Email / ID Num.
Patron
Md Badarudin, Ismadi
UNSPECIFIED
Advisor
Jasmis, Jamaluddin
UNSPECIFIED
Advisor
Jono, Mohd Hajar Hasrol
UNSPECIFIED
Director
Suhaimi, Nur Suhailayani
UNSPECIFIED
Team Member
Mat Zain, Nurul Hidayah
UNSPECIFIED
Team Member
Abdullah Sani, Anis Shobirin
UNSPECIFIED
Team Member
Halim, Faiqah Hafidzah
UNSPECIFIED
Team Member
Abd Kadir, Siti Aisyah
UNSPECIFIED
Team Member
Jalil, Ummu Mardhiah
UNSPECIFIED
Subjects: T Technology > T Technology (General) > Integer programming
Divisions: Universiti Teknologi MARA, Melaka > Jasin Campus > Faculty of Computer and Mathematical Sciences
Event Title: nternational Jasin Multimedia & Computer Science Invention and Innovation Exhibition (i-JaMCSIIX 2023)
Event Dates: 8th November 2023
Page Range: p. 42
Keywords: Artificial Neural Network; Forecasting; Inflation rate; Hidden layer; Model parsimony
Date: 2023
URI: https://ir.uitm.edu.my/id/eprint/93959
Edit Item
Edit Item

Download

[thumbnail of Abstract Only] Text (Abstract Only)
93959.pdf

Download (2MB)

ID Number

93959

Indexing

Statistic

Statistic details