Journal of Statistical Methods and Data Science

K-MEANS CLUSTERING USING ELBOW METHOD IN CASE OF DIABETES MILLETUS TYPE II IN INDONESIA

2023-06-07T15:06:01+00:00

Indonesia is ranked 7th out of 10 countries with the
highest number of sufferers. BPJS Health include First Level
Health Facilities (FKTP) and Advanced Referral Health
Facilities (FKRTL) which Type 2 diabetes mellitus is one of
the ten most common diagnoses at FKRTL visits and ranks
third after follow-up examinations after treatment for
conditions other than malignant neoplasms and kidney failure
with a percentage of 3.54% and a total of 62,455 for 2019 to
2020. In deciding policies related to the funding of BPJS
participants who suffer from diabetes mellitus, it is necessary
to have the characteristics of each region so that policy making
is more appropriate. The method used in this study uses
clustering analysis using the K-means algorithm for type
II diabetes mellitus in Indonesia from 2015-2020 by
province. Based on the outcome of the clustering
provinces in indonesia using K-Means algorithm with
optimization of the determination of the number of
cluster using elbow method formed 3 cluster. 1 st cluster has
21 province, the 2 nd cluster has 9 province and the 3 rd cluster
has 4 province.

APPLICATION OF THE FUZZY TIME SERIES CHEN MODEL IN FORECASTING THE RUPIAH EXCHANGE RATE AGAINST THE US DOLLAR (USD)

2024-03-20T07:04:20+00:00

The importance of the rupiah exchange rate for many individuals in Indonesia in everyday life can be explained by the fact that the country's economy is very dependent on the international economy. Exchange rate used to do future payments using a certain currency and so on the link between two currencies of different countries. In context In international trade, the US Dollar (USD) currency has a very important role very significantly for developing countries because it is used as an eye transaction money. Therefore, the movement of the rupiah exchange rate is an important factor for a country. So forecasting techniques are needed to anticipate exchange rate changes. In this study, the method used is Chen's Fuzzy Time Series (FTS) model to predict the rupiah exchange rate against the United States Dollar (USD) in the future. The results of this study show that forecasting the rupiah exchange rate against the US Dollar (USD) from May 2023 to July 2023 is stable at a value of 1412.40 Rupiah, with a rate average absolute error (MAPE) of 1.6717%.

AUTOMATIC WEIGHT CRITERIA FOR SAW-BASED DECISION SUPPORT SYSTEM USING GRADIENT DESCENT

2024-03-20T09:46:15+00:00

Modern organizations always utilize a Decision Support Systems (DSS) to have informed decision-making. The Simple Additive Weighting (SAW) method is a prevalent approach used in DSS for evaluating alternatives based on specific criteria. However, the subjectivity inherent in determining criteria weights in SAW poses a significant challenge. This research introduces a new approach, combining the SAW method with Gradient Descent to automatically determine criteria weights. By doing so, it takes advantage of the similarities between SAW and linear equations. Our research shows that this method produces more accurate and unbiased criteria weights, as confirmed by the Mean Square Error (MSE) analysis. In conclusion, incorporating Gradient Descent into the Decision Support System has the potential to greatly improve its effectiveness by automating the criteria weight determination process in various decision-making scenarios, leading to more accurate and less subjective decision support in organizations.

IMPLEMENTATION OF THE RANDOM FOREST METHOD FOR PREDICTING STUDENTS’ LENGTH OF STUDY

2024-03-20T05:56:17+00:00

Predicting a student's duration of study is essential for universities to ensure students complete their studies on time. This research aims to develop an effective prediction model for determining the length of study based on related factors. To overcome the complexity and diversity of student data, the Random Forest method was chosen. The results indicate that the Random Forest method is an effective tool for predicting the duration of study for university students. A study was conducted on 1,535 graduates from the five departments at the Faculty of Mathematics and Natural Sciences, Riau University. The study employed cross-validation techniques to measure model performance. The model's accuracy was evaluated using a confusion matrix, which revealed that the Random Forest model had an average accuracy of 95.12%. Additionally, feature importance analyses identified grade point average in the eighth semester as a major contributor to the prediction outcome.

IMPLEMENTATION OF GEOGRAPHICALLY WEIGHTED LASSO (GWL) IN ANALYZING RICE PRODUCTION FACTORS IN INDONESIA

2024-03-30T08:20:05+00:00

Geographically Weighted Lasso (GWL) is a combination of two regression methods, namely Geographically Weighted Regression (GWR) and Least Absolute Shringkage Selection Operator (LASSO). Both methods have their own uses. GWR is a regression that takes into account the geographical location aspect because the spatial heterogeneity test is not met. LASSO is a regression method to overcome multicollinearity in the data. The two problems are simultaneously contained in one regression model, namely the GWL method. This study will analyze the factors that affect rice production in 34 provinces in Indonesia by applying and interpreting the results of the Geographically Weighted Lasso method. The results of the analysis show that the coefficient of determination of the GWL model is 0.9703 so it can be concluded that the explanatory variables in this study can that the global level of rice production in each province in Indonesia is 97.03%.