Abstract:Abstract: M-Forecasting or Mobile Forecasting can be interpreted as mobile-based forecasting. Forecasting here means predicting a situation in the future. The use of mobile technology in forecasting is considered appropriate…
iate to improve the efficiency of forecasting to be carried out, this is supported by the development of increasingly mobile technology, where digital marketing marketing research institutions estimate that in 2018 the number of active smartphone users in Indonesia is more than 100 million people. This fantastic amount can be utilized by the development of mobile-based information systems for forecasting. Predictions of a forecast can be realized by using several methods. The Weighted Moving Average method is one of them. This method provides predictions for the future by utilizing previous data and giving different weights for each data used. The level of confidence in forecasting can be determined by measuring the error percentage of the forecasting obtained. The higher the error rate can be interpreted that the forecasting results obtained are increasingly unreliable or inaccurate, and vice versa. This forecasting technique can be applied in various fields of work, including in forecasting rubber production. By obtaining forecasting data on rubber production in the future, of course, it can provide an overview of future work steps, so that it can increase the company's work productivity. Based on this, the researchers intend to build a mobile-based forecasting application system, so that it can be installed in a mobile device later, especially mobile technology with the Android operating system.
Keywords: Forecasting, Mobile, Android, Weighted Moving Average.
Abstrak: M-Forecasting atau Mobile Forecasting dapat diartikan sebagai peramalan berbasis mobile. Peramalan disini berarti memprediksi suatu keadaan dimasa mendatang. Penggunaan teknologi mobile dalam peramalan dianggap tepat untuk meningkatkan efisiensi peramalan yang akan dilakukan, hal ini didukung dengan perkembangan teknologi mobile yang kian pesat, dimana lembaga riset digital marketing emarketer memperkirakan pada 2018 jumlah pengguna aktif smartphone di Indonesia lebih dari 100 juta orang. Jumlah yang fantastis ini dapat dimanfaatkan dengan pengembangan sistem informasi berbasis mobile untuk peramalan. Prediksi dari sebuah peramalan dapat terwujud dengan penggunaan beberapa metode. Metode Weighted Moving Average adalah salah satunya. Metode ini memberikan prediksi masa depan dengan memanfaatkan data-data terdahulu dan memberikan bobot yang berbeda-beda untuk setiap data yang digunakan. Tingkat kepercayaan peramalan dapat diketahui dengan mengukur persentase eror dari peramalan yang diperoleh. Semakin tinggi tingkat eror dapat diartikan bahwa hasil peramalan yang diperoleh semakin tidak dapat dipercaya atau tidak akurat, begitu juga sebaliknya. Teknik peramalan ini dapat diterapkan diberbagai bidang pekerjaan, termasuk dalam peramalan produksi karet. Dengan memperoleh data peramalan produksi karet dimasa mendatang tentunya dapat memberikan gambaran untuk langkah-langkah kerja kedepannya, sehingga dapat meningkatkan produktivitas kerja perusahaan. Berdasarkan hal tersebut, peneliti bermaksud membangun sebuah sistem aplikasi peramalan berbasis mobile, sehingga dapat dipasang diperangkat mobile nantinya, khususnya teknologi mobile dengan sistem operasi android.
Kata Kunci: Forecasting, Mobile, Android, Weighted Moving Average.
Abstract:Tourism is one of the most important factors for the revenue of an area. To attract the interest of tourists takes some supporting factors, one of which is the hotel or the guesthouse. In the process of prediction of tourists…
rists visit, required data the number of tourists staying in order to predict for the next time. The prediction method used in this system is a method of Backpropagation Neural Network based on time series data forecasting component variansi random or random process beginning with autocorrelation for determination of input variables. Method of Backpropagation itself is known quite well used in the forecasting of time series data. The result of the method of Backpropagation is a number of predictions that tourists visit can be a reference for related officials in taking decisions for the period ahead.
Abstract:Abstract: There are several facilities in distributing funds to the customer which is owned by Bank Syariah Bukopin. One of them is Kredit Pemilikan Rumah / Housing Loan (mortgage), so far the bank when provides mortgages…
s to customers still uses risk prediction manually in giving credit to customers which is taking up a lot of time and energy especially when the customer reports is further analyzed by the Bank. One technique that can help in predicting the Bank's credit risk determination is Decision Tree which is a technique that is a part of Data Mining techniques to take a decision in the form of a tree. With Decision Tree techniques, it is expected to help the bank to allow faster and easier in predicting the data and getting a conclusion from existing data. One of the ways to predict the data is using Dtreg software. This software only uses data that is in the format of "csv (comma delimited)â€, if it is not using the format" csv (comma delimited)", so that the data can not be processed by Dtreg software. When the excel format has been converted to the "csv (comma delimited)" format, the analysis process can be done. Dtreg can generate decision tree, one of them is the result of risk decision from the number of mortgages based on the number of customers.
Keywords: data mining, decision tree
Abstrak: Ada beberapa fasilitas dalam penyaluran dana ke nasabah yang di miliki Bank Syariah Bukopin. Salah satunya Kredit Pemilikan Rumah (KPR), selama ini pihak Bank memberikan KPR ke nasabah masih menggunakan prediksi resiko secara manual dalam meberikan kredit kepada nasabah yang banyak menyita waktu dan tenaga apalagi pada saat laporan nasabah dianalisa lebih lanjut oleh pihak Bank. Salah satu teknik yang dapat membantu pihak Bank dalam memprediksi Penentuan resiko kredit adalah teknik Decision Tree yang merupakan bagian dari teknik Data Mining untuk mengambil suatu keputusan dalam bentuk pohon. Dengan teknik Decision Tree diharapkan dapat membantu pihak bank agar lebih cepat dan mudah dalam memprediksi data dan menarik suatu kesimpulan dari data yang ada.Salah satu cara memprediksi data tersebut dengan menggunakan software Dtreg. Pada software ini data yang digunakan hanya bisa dalam bentuk format “csv (comma delimited), jika tidak menggunakan format “csv (comma delimited)“ maka data tersebut tidak bisa diproses oleh software Dtreg dan selanjutnya jika format excel yang telah dirubah ke format “csv (comma delimited)â€, maka akan dapat dilakukan proses analisa. Dtreg dapat menghasilkan pohon keputusan, salah satu nya yaitu hasil keputusan resiko dari jumlah kredit pemilikan rumah berdasarkan jumlah nasabah.
Kata kunci: data mining, decision tree
Abstract:This study investigates the stress concentration factor in an infinite steel plate with a thickness of 1 cm, containing an elliptical hole, subjected to biaxial loading at infinity. The elliptical hole has semi-axes a=5.0 cma…
0 cma = 5.0 \, \text{cm}a = 5.0 cm (major axis) and b=2.5 cmb = 2.5 \, \text{cm}b = 2.5 cm (minor axis). The applied stresses at infinity are a tensile stress of σ1=100 kg/cm2\sigma_1 = 100 \, \text{kg/cm}^2= 100 kg/parallel to the major axis and a compressive stress of σ2=−100 kg/cm2\sigma_2 = -100 \, \text{kg/cm}^2= -100 kg/ perpendicular to the major axis. The material properties include Young's modulus E=2.1×106 kg/cm2E = 2.1 \times 10^6 \, \text{kg/cm}^2E = 2,1. kg/ and Poisson's ratioν=0.3\nu = 0.3 = 0.3. Using analytical solutions from classical elasticity theory, the maximum tangential stress at the edge of the ellipse is calculated as σmax=600 kg/cm2\sigma_{\text{max}} = 600 \, \text{kg/cm}^2= -600 kg/, yielding a stress concentration factor of kσ=σmax/σ=6k_\sigma = \sigma_{\text{max}} / \sigma = 6 = =6. Additionally, a finite element (FE) analysis based on the Salerno and Sahoni problem for a quarter section of the plate results in kσ=3.1125k_\sigma = 3.1125 = 3.1125 for a configuration with s/r=5s/r = 5s/r = 5, showing a discrepancy of 1.3% compared to the theoretical value of kσ=3.1k_\sigma = 3.1= 3.1 from Peterson's Stress Concentration Factors. The results demonstrate good agreement between the calculated model and theoretical predictions, validating the accuracy of the FE approach for stress concentration analysis in such configurations.
Abstract:The rapid advancement of artificial intelligence (AI) has significantly impacted the healthcare sector, particularly in supporting the early detection of diabetes; however, many AI models still face challenges due to their…
ir black-box nature, where decision-making processes are not easily understood. This study aims to compare two Explainable Artificial Intelligence (XAI) methods, namely Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive Explanations (SHAP), in interpreting the prediction results of an Artificial Neural Network (ANN) model using the Diabetes Health Indicator dataset. Prior to modeling, the data were preprocessed through cleaning and normalization to ensure quality and consistency. The trained ANN model was then analyzed using LIME and SHAP to evaluate the contribution of each feature to the prediction outcomes. The results show that both methods are capable of providing meaningful and interpretable explanations, although SHAP demonstrates more consistent and stable interpretations across the dataset. These findings highlight the importance of integrating XAI techniques to enhance model transparency, thereby increasing trust and supporting more reliable decision-making in clinical settings, particularly for diabetes diagnosis.
Abstract:This paper explores the role of Artificial Intelligence (AI) in enhancing decision-making processes within multinational corporations. The primary issue addressed is how AI can be integrated effectively across diverse global…
obal markets, considering factors like regulatory frameworks, cultural diversity, and market dynamics. The research proposes a framework for AI implementation that ensures both operational efficiency and ethical soundness. The study employs a mixed-methods approach, combining qualitative interviews and quantitative surveys from key stakeholders in multinational corporations. Preliminary findings suggest that AI significantly improves decision-making speed and accuracy, particularly in data analysis, market trend prediction, and consumer behavior forecasting. However, challenges remain in adapting AI systems to various cultural and regulatory environments, highlighting the need for customization and local adjustments. This study contributes to understanding how AI can be applied more effectively and ethically across international markets, offering insights for future implementations in diverse business contexts.