Garuda - Garba Rujukan Digital

Mhd Ali Hanafiah

Politeknik Bisnis Indonesia, Pematangsiantar, Indonesia

Author-ID : 2511247

Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Social Sciences

Published : 6 Documents Claim Missing Document

Claim Missing Document

Articles

Title

1

Analysis of ANN Backpropagation Ability to Predict Expenditure Group Inflation Mhd Ali Hanafiah; Ni Luh Wiwik Sri Rahayu Ginantra; Achmad Daengs GS
IJISTECH (International Journal of Information System and Technology) Vol 4, No 2 (2021): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

The Covid-19 pandemic that has hit the world, especially Indonesia, has greatly disturbed the stability of the inflation rate. Inflation that continues to increase will disrupt the economy in this country. Therefore this study aims to analyze the ability of ANN backpropagation which will be applied to predict the development of the inflation in Indonesia during the Covid-19 pandemic so that later it can be useful information for the government and society. The research data used is inflation data according to expenditure groups obtained from CBS (Central Statistics Agency) in January-May 2020. Prediction is done using the backpropagation neural network algorithm. This paper uses four network architectures, namely: 3-5-1, 3-10-1, 3-25-1 and 3-50-1. Based on the training and testing of the four models, the 3-10-1 model is the best architectural model that is suitable for predicting the development of the inflation in Indonesia with an accuracy of 75%. Also, this model performs an iteration of 25303 and an MSE test of 0.0362820326. Based on the prediction results in June-August 2020 and real data obtained from the Central Statistics Agency, ANN using the backpropagation method is highly recommended to be used to predict the development of Indonesian Inflation according to the Expenditure Group.

Implementation of Data Mining Algorithms for Grouping Poverty Lines by District/City in North Sumatra Mhd Ali Hanafiah; Anjar Wanto
IJISTECH (International Journal of Information System and Technology) Vol 3, No 2 (2020): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

The poverty line is useful as an economic tool that can be used to measure the poor and consider socio-economic reforms, such as welfare programs and unemployment insurance to reduce poverty. Therefore, this study aims to classify poverty lines according to regencies/cities in North Sumatra Province, so that it is known which districts/cities have high or low poverty lines. The grouping algorithm used is K-Means data mining. By using this algorithm, the data will be grouped into several parts, where the process of implementing K-Means data mining uses Rapid Miner. The data used is the poverty line data by district/city (rupiah/capita/month) in the province of North Sumatra in 2017-2019. Data sourced from the North Sumatra Central Statistics Agency. The grouping is divided into 3 clusters: high category poverty line, medium category poverty line, and the low category poverty line. The results for the high category consisted of 5 districts/cities, the medium category consisted of 18 districts/cities and the medium category consisted of 10 districts/cities. This can provide input and information for the North Sumatra government to further maximize efforts to overcome the poverty line in the area.

K-Medoids: Inflation Clustering of 90 Cities in Indonesia (January-October 2020) Mhd Ali Hanafiah
IJISTECH (International Journal of Information System and Technology) Vol 4, No 1 (2020): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Inflation affects society and the economy of a country. For the general public, inflation is a concern because inflation directly affects the welfare of life, and for the business world, the inflation rate is a very important factor in making various decisions. Therefore, the aim of this study is to cluster the inflation rate that occurs in 90 cities in Indonesia, so that it is known which cities have high, medium, or low inflation levels. The grouping algorithm used is K-Medoids data mining. The research data is quantitative data, namely inflation data that occurred in 90 major cities in Indonesia from January to October 2020. The data was obtained from the Indonesian Central Statistics Agency. The clustering in this study is divided into 5, among others: cities with very high inflation rates, cities with high inflation rates, cities with moderate inflation rates, cities with low inflation rates, and cities with very low inflation rates. Based on the results of clustering analysis using rapidminer, for cities with a very high inflation rate category consists of 1 city (available on Cluster_4), high category consists of 4 cities (Cluster_0), medium category consists of 4 cities (Cluster_3), low category consists of 79 cities (Cluster_2) and very low category consisted of 2 cities (Cluster 1). This can provide information for the Indonesian government to keep the inflation rate stable.

Title Search

Found 3 Documents Search Journal : IJISTECH (International Journal Of Information System

Abstract

Abstract

Abstract

Title

Found 3 Documents
Search
Journal : IJISTECH (International Journal Of Information System