VARIANSI: Journal of Statistics and Its application on Teaching and Research

Peramalan Suhu Rata – Rata Kota Padang Panjang dengan Membandingkan Metode SARIMA dan Holt – Winter Additive

Fadhira Vitasha Putri — 2024-12-06

Padang Panjang City, situated at an altitude of 650 to 850 meters above sea level and surrounded by high mountains, experiences significant temperature changes that affect various aspects of life such as public health, agriculture, and tourism. This study aims to forecast the monthly average temperature of Padang Panjang City from January 2017 to December 2023 by comparing SARIMA and Holt-Winters Additive forecasting methods. The results show that the SARIMA method, with an MSD value of 0.2206, is more accurate compared to the Holt-Winters Additive method, which has an MSD value of 0.29821. With the SARIMA model as the best method, the forecast indicates that the highest average temperature in Padang Panjang City will reach 23.1418 degrees Celsius in May 2024. These results are expected to provide a strong basis for planning and decision-making related to the temperature changes occurring in Padang Panjang City.

Penerapan Extreme Learning Machine (ELM) untuk Meramalkan Laju Inflasi di Indonesia

Muhammad Fahmuddin S — 2024-12-31

Inflation is generally the tendency for the prices of goods and services to rise continuously. An artificial neural network (ANN) is an information processing model that closely resembles how an organism's memory system works, such as information transmission processes in the brain. Forecasting is the activity of determining future events based on past data. A time series is a set of observations that occur consecutively in the correct amount of time based on a time index. The data used in this study are Indonesian monthly inflation data. Extreme Learning Machine (ELM) is an artificial neural network approach that uses a single hidden layer feedforward neural network architecture (SLFN). The advantages of ELM over traditional learning algorithms are learning speed, improved generalization performance, and simplified implementation. An error value of RMSE of 0.1992215 was obtained based on the analysis performed using the Extreme Learning Machine (ELM) method.

Perbandingan Metode ARIMA dan Single Exponential Smoothing dalam Peramalan Nilai Ekspor Kakao Indonesia

Muhammad Fahmuddin S — 2024-12-31

Indonesia is a country with an open economy, one of the sources of foreign exchange needed by a country with an open economy is exports. Cocoa is one of Indonesia's main export commodities that makes an important contribution to the country's economy, but the value of Indonesian cocoa exports fluctuates, that is there are inconsistent changes from time to time. The purpose of this study is to determine the results of forecasting the value of Indonesian cocoa exports, as well as to determine the best method for forecasting. This research compares the ARIMA and Single Exponential Smoothing methods to determine the best forecasting method. The best method is selected based on the smallest MAPE value. Based on the results of data analysis, the best forecasting model using the ARIMA method is the ARIMA (1, 0, 1) model, which has a MAPE value of 10.38060%. Meanwhile, the best forecasting model using the Single Exponential Smoothing method is with α = 0.16, which has a MAPE value of 10.92874%. So that the best method for forecasting the value of Indonesian cocoa exports is the ARIMA method.

Algoritma K-Prototype dalam Pengelompokan Kabupaten/Kota di Provinsi Sulawesi Selatan Berdasarkan Indikator Kesejahteraan Rakyat Tahun 2020

Zulkifli Rais — 2024-12-31

Clustering is something that is used to analyze data both in machine learning, data mining, pattern engineering, image analysis and bioinformatics. To produce the information needed for a data analysis using the clustering process, this is because the data has a large variety and amount. Researchers will use the K-Prototype method where this method becomes an efficient and effective algorithm in processing mixed-type data. The K-Prototype algorithm has problems in finding the best number of clusters. So, in this paper, researchers will conduct research by finding the best number of clusters in the K-Prototype method. There are many ways to determine this, one of which is the Elbow method. The determination of this method is seen from the SSE (Sum Square Error) graph of several number of clusters. The results of the clustering formed 2 clusters which were considered optimal based on the value of k that experienced the greatest decrease. The results showed that, cluster 1 is a cluster that has characteristics of people's welfare which is better than cluster 2.