Yunizar, Mahdayani Putri
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

PERFORMANCE ANALYSIS OF RANDOM FOREST CLASSIFICATION ON UNEMPLOYMENT RATE IN MALUKU PROVINCE BASED ON DATA BALANCING METHOD Yunizar, Mahdayani Putri; Sinay, Lexy Janzen; Yudistira, Yudistira
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 1 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss1page31-38

Abstract

In 2023, the number of unemployed people in Maluku will reach 59,800 or 6.08% of the total population. To reduce unemployment in Maluku, it is essential to understand the unemployment situation of the Moluccan population based on socioeconomic factors immediately. Therefore, applying classification methods such as random forests is the right step, but it is recommended that the data be balanced to get accurate results. However, the unemployment rate in Maluku is much lower than that of the unemployed, so data imbalance affects the accuracy of the classification results. Therefore, a data balancing process is needed, among others, using the Random Oversampling of Sample (ROSE), Synthetic Minority Oversampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN) methods. This study uses data from the 2023 National Labor Force Survey (SAKERNAS) conducted in February by the Central Statistics Agency (BPS) of Maluku. The number of unemployed people is smaller than the number of unemployed residents. Therefore, action needs to be taken to address data inequality. The results of this study show that the random forest classification model with SMOTE has the best performance with a combination of 90% training data and 10% testing data, with a higher AUC value than other methods, and age variables are the most essential variables built into the model.
Enhancing Rainfall Forecasting Performance in Bandung City Using Bi-LSTM with Grid Search Optimization on Gregorian and Lunar Calendar Data Yunizar, Mahdayani Putri; Talakua, Andrew Hosea; Darmawan, Gumgum
Parameter: Jurnal Matematika, Statistika dan Terapannya Vol 4 No 3 (2025): Parameter: Jurnal Matematika, Statistika dan Terapannya
Publisher : Jurusan Matematika FMIPA Universitas Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/parameterv4i3pp595-601

Abstract

Rainfall is a climatic factor that strongly influences human activities and plays a crucial role in decision making related to water resources, mobility, and disaster preparedness. High rainfall intensity may escalate into hydrometeorological hazards, underscoring the importance of accurate rainfall forecasting to support early warning and mitigation efforts. This study aims to compare the forecasting accuracy of monthly rainfall predictions between the Gregorian and lunar calendars using the Bidirectional Long Short-Term Memory (Bi-LSTM) model optimized through a grid search approach. The method is designed to capture temporal patterns arising from the distinct structures of two asynchronous calendars. Daily rainfall data from Bandung City, Indonesia, covering the period from 2000 to 2025, were converted into monthly series in both calendar systems. The results reveal that the Gregorian calendar provides significantly better forecasting performance, achieving the lowest MAPE value of 11.60 percent at the three-month horizon. In contrast, the lunar calendar shows higher variability and reaches its best MAPE of 31.43 percent at the same horizon. These findings indicate that the Gregorian calendar offers a more stable temporal representation for rainfall forecasting in Bandung and supports improved predictive modeling for climate-related decision making.