Syarifah Diana Permai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Syarifah Diana Permai has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Ajeng Wulandari
Bina Nusantara University
2 shared publications - Alexander Agung Santoso Gunawan
Computer Science Department, School of Computer Science, Bina Nusantara University, Jakarta, Indonesia
1 shared publication - Felix Indra Kurniadi
Universitas Bina Nusantara Jakarta Indonesia
1 shared publication Hansel Hosea
School of Computer Science Bina Nusantara University,Computer Science Department,Jakarta,Indonesia,11480
1 shared publication- Kartika Purwandari
Bina Nusantara University
1 shared publication - Margaretha Ohyver
Bina Nusantara University
1 shared publication
Latest Publications
- Open Access
- 1 March 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (1) , 348-357
Sampling methods in handling imbalanced data for Indonesia health insurance dataset
Health insurance fraud is one of the most frequently occurring fraudulent acts and has become a concern for every insurance. According to data from The Indonesian General Insurance Association or Asosiasi Asuransi Umum Indonesia (AAUI), the private insurance industry suffered losses up to billions rupiah throughout 2018 due to the fraudulent acts commited by the perpetrators. The problem in with the number of frauds in Indonesia is that the current system is highly vulnerable and they is still done manually. The other problem from this detection is imbalance data which often occurs in fraudulent cases. In this research, we used a sampling methods using several machine learning as the baseline. The result shows that the instance hardness thresholding algorithm and extreme gradient boosting gives the best performance for all the case. It shows the method can reduced the bias and can achieve better generalization.
- 1 March 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (1) , 348-357
Open AccessSampling methods in handling imbalanced data for Indonesia health insurance dataset
Health insurance fraud is one of the most frequently occurring fraudulent acts and has become a concern for every insurance. According to data from The Indonesian General Insurance Association or Asosiasi Asuransi Umum Indonesia (AAUI), the private insurance industry suffered losses up to billions rupiah throughout 2018 due to the fraudulent acts commited by the perpetrators. The problem in with the number of frauds in Indonesia is that the current system is highly vulnerable and they is still done manually. The other problem from this detection is imbalance data which often occurs in fraudulent cases. In this research, we used a sampling methods using several machine learning as the baseline. The result shows that the instance hardness thresholding algorithm and extreme gradient boosting gives the best performance for all the case. It shows the method can reduced the bias and can achieve better generalization.
- 3 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 1-4
Analyzing Poverty Rate Using ANOVA in Indonesia
Poverty is one of the major problems in most countries around the world, especially Indonesia. Many factors have caused poverty, such as low education level, low rate of income, and inequality. Based on the data from BPS Indonesia, the poverty rate in 2012 was 11.96% over the population and the poverty rate in 2020 was 9.84% over the population. Based on the data, the government has successfully decreased the poverty rate in Indonesia. This study is trying to analyze the poverty rate in Indonesia from 2012–2020 using ANOVA to look at the difference in the poverty rate from provinces and years as the subject whether the poverty rate in Indonesia is actually decreasing or not before the pandemic. The result showed the poverty rate in Indonesia is not change from 2012–2020 based on years by using one-way ANOVA. The result showed that F value is 0.877 and p-value is 0.535. The p-value is greater than $a$ = 0.05 then do not reject H0. It showed that there is no difference between years in the poverty rate. If the result used the province as the subject in one-way ANOVA, it showed a significant differences between poverty rates in the provinces. Because the F value is 737.4 and p-value < 2 x 10-16• Then p-value is less than 0.05. It means that H0 is rejected. It can be concluded that the poverty rate in each province is different. It can be concluded that the poverty rate in Indonesia did not change significantly in 9 years. But the result of two way ANOVA showed that the year, province and interaction between year and province are significant. It means that the difference between year and province is impacting the poverty rate in Indonesia.- 3 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 1-4
Analyzing Poverty Rate Using ANOVA in Indonesia
Poverty is one of the major problems in most countries around the world, especially Indonesia. Many factors have caused poverty, such as low education level, low rate of income, and inequality. Based on the data from BPS Indonesia, the poverty rate in 2012 was 11.96% over the population and the poverty rate in 2020 was 9.84% over the population. Based on the data, the government has successfully decreased the poverty rate in Indonesia. This study is trying to analyze the poverty rate in Indonesia from 2012–2020 using ANOVA to look at the difference in the poverty rate from provinces and years as the subject whether the poverty rate in Indonesia is actually decreasing or not before the pandemic. The result showed the poverty rate in Indonesia is not change from 2012–2020 based on years by using one-way ANOVA. The result showed that F value is 0.877 and p-value is 0.535. The p-value is greater than $a$ = 0.05 then do not reject H0. It showed that there is no difference between years in the poverty rate. If the result used the province as the subject in one-way ANOVA, it showed a significant differences between poverty rates in the provinces. Because the F value is 737.4 and p-value < 2 x 10-16• Then p-value is less than 0.05. It means that H0 is rejected. It can be concluded that the poverty rate in each province is different. It can be concluded that the poverty rate in Indonesia did not change significantly in 9 years. But the result of two way ANOVA showed that the year, province and interaction between year and province are significant. It means that the difference between year and province is impacting the poverty rate in Indonesia.- Open Access
- 1 July 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1988 (1) , 012040
Daily rainfall modeling using Neural Network
In the early 2020, Indonesia experienced flooding in several areas. This disaster caused a lot of damage and losses. One of the causes of flooding in Indonesia is due to high rainfall. This was not anticipated beforehand so there was a flood. Therefore, research on rainfall in Indonesia is very important to anticipate floods. If it is predicted that rainfall is very high and conditions do not allow it to accommodate, the government can prepare watersheds so that rainwater can flow and not be trapped. In this research, the rainfall data were obtained from Meteorological, Climatological, and Geophysical Agency (BMKG Indonesia), then the analysis of rainfall data in Indonesia was carried out. There are several statistical methods that can be used. There are ARIMA and Neural Network. In this research, the results of ARIMA model are used as input variables in the Neural Network model. Then there are several numbers of hidden layer in the Neural Network model that are compared. The results of ARIMA model and Neural Network model showed that Neural Network model is better than ARIMA model, because the mean square error (MSE) value of Neural Network model is smaller than ARIMA model.
- 1 July 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1988 (1) , 012040
Open AccessDaily rainfall modeling using Neural Network
In the early 2020, Indonesia experienced flooding in several areas. This disaster caused a lot of damage and losses. One of the causes of flooding in Indonesia is due to high rainfall. This was not anticipated beforehand so there was a flood. Therefore, research on rainfall in Indonesia is very important to anticipate floods. If it is predicted that rainfall is very high and conditions do not allow it to accommodate, the government can prepare watersheds so that rainwater can flow and not be trapped. In this research, the rainfall data were obtained from Meteorological, Climatological, and Geophysical Agency (BMKG Indonesia), then the analysis of rainfall data in Indonesia was carried out. There are several statistical methods that can be used. There are ARIMA and Neural Network. In this research, the results of ARIMA model are used as input variables in the Neural Network model. Then there are several numbers of hidden layer in the Neural Network model that are compared. The results of ARIMA model and Neural Network model showed that Neural Network model is better than ARIMA model, because the mean square error (MSE) value of Neural Network model is smaller than ARIMA model.