#### Journal of Mathematics : Theory and Application

Journal Information
ISSN / EISSN: 26859653 / 27222705
Total articles ≅ 35

#### Latest articles in this journal

Published: 17 November 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 50-56; https://doi.org/10.31605/jomta.v4i2.2010

Abstract:
Claims are a form of demands from insurance policy holders in order to get protection against financial losses due to risks that occur. Claims that arise every time a risk occurs are called individual claims, while the total of individual claims during an insurance period is called aggregation claims. In addition, claims are one of the important elements in optimizing the minimum expenditure of insurance companies where one of the calculations that insurance companies need to know based on claims is aggregate loss. Aggregate loss is the total loss in a period experienced by the policyholder which is borne by an insurance company. This study aims to determine the estimated total aggregate loss claims for the number of claims with a Negative Binomial distribution and the size of the claims with a Discrete Uniform distribution in the recapitulation of claim payments according to all types of guarantees and the nature of injuries in 2018-2020 PT. Jasa Raharja, Purwakarta. This study uses the convolution method with the help of Easyfit and R Studio software. The convolution method is a method of calculating the number of multiplication pairs of a probability density function. The results of this study indicate that from the recapitulation data on claim payments according to all types of insurance and nature of injury in 2018-2020 PT. Jasa Raharja, Purwakarta, the estimated total monthly aggregate loss claims for the years 2021-2023 using Jasa Raharja's insurance claim data from 2018 to 2020 based on the Negative Binomial distribution and the Discrete Uniform distribution is IDR 4,278,5545,000 and the variance value of 2.128412e-06.
, Reski Wahyu Yanti, Syandriana Syarifuddin
Published: 14 November 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 45-49; https://doi.org/10.31605/jomta.v4i2.2030

Abstract:
Indeks Pembangunan Manusia (IPM) merupakan ukuran kunci untuk mengukur keberhasilan upaya peningkatan kualitas hidup penduduk. IPM dapat menentukan peringkat atau tingkat perkembangan suatu wilayah/negara. Indeks Pembangunan Manusia (IPM) mengukur kinerja pembangunan manusia berdasarkan banyak komponen dasar kualitas hidup. Indeks Pembangunan Manusia (IPM) juga merupakan indikator penting untuk mengukur keberhasilan upaya peningkatan kualitas hidup. Penelitian ini menggunakan metode regresi random forest dengan tingkat kepentingan peubah prediktor diukur menggunakan nilai Shapley Addictive Explanation (SHAP). Hasil penelitian menunjukkan bahwa dari keempat faktor-faktor yang mempengaruhi IPM, peubah pengeluaran per kapita (X1) memiliki tingkat kepentingan tertinggi dan yang terendah adalah peubah angka harapan lama sekolah (X3). Sementara rata-rata lama sekolah (X2) dan umur harapan hidup saat lahir (X4) memiliki tinkat kepentingan berturut-turut kedua dan ketiga terhadap IPM di Indonesia.
Published: 14 November 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 40-44; https://doi.org/10.31605/jomta.v4i2.2035

Abstract:
Tujuan dari kajian ini adalah untuk mengkonstruksi model SEIRS pada penyebaran Covid-19 di Kabupaten Bulukumba dengan mempertimbangkan penerapan protocol kesehatan. Analisis model menggunakan matriks next generasi untuk memperoleh bilangan reproduksi dasar dan kestabilan dari titik ekuilibrium model. Hasil simulasi menunjukkan bahwa penerapan protocol kesehatan yang efektif, yaitu lebih dari 21%, akan dapat menghambat laju penularan Covid-19 di Kabupaten Bulukumba.
, Darma Ekawati
Published: 14 November 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 35-39; https://doi.org/10.31605/jomta.v4i2.2031

Abstract:
Published: 11 November 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 30-34; https://doi.org/10.31605/jomta.v4i2.2019

Abstract:
Abstrak. Tulisan ini membahas tentang teorema titik tetap untuk pemetaan bernilai himpuanan dengan domain berupa subset dari suatu ruang b-metrik. Hasil yang diperoleh merupakan pengembangan dari hasil yang telah diperoleh pada literatur terdahulu. Kata kunci: b-metrik, pemetaan bernilai himpuan, teorema titik tetap. This paper study about fixed point theorem for set-valued maps where its domain is subset of a b-metric space. The result is improvement from the literature. Keywords: b-metric, set-valued maps, fixed point theorem.
, Oni Soesanto, Yuana Sukmawaty
Published: 28 August 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 21-26; https://doi.org/10.31605/jomta.v4i1.1792

Abstract:
Bad credit card is a problem of inability of credit card users to pay credit card bills that can cause losses to both parties concerned. In order to avoid losses caused by bad credit cards, the provider must conduct a careful analysis of prospective or old customers using credit cards. This study aims to classify bad credit card customers using machine learning techniques, namely classification techniques. One of the classification techniques used is the XGBoost method which is useful for regression analysis and classification based on the Gradient Boosting Decision Tree (GBDT), the XGBoost method has several hyperparameters that can be configured to improve the performance of the model. Hyperparameter tuning method used is grid search cross validation which is then validated using 10-Fold Cross Validation. XGBoost hyperparameters configured include n_estimators, max_depth, subsample, gamma, colsample_bylevel, min_child_weight and learning_rate. Based on the results of this study proves that the use of algorithms with hyperparameter tuning can improve the performance of eXtreme Gradient Boosting algorithm in the process of classification of credit card customers with an accuracy of 80.039%, precision of 81.338% and a recall value of 96.854%. Keywords: XGBoost, classification, Accuracy, Precision, Recall
Published: 28 August 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 27-29; https://doi.org/10.31605/jomta.v4i1.1878

Abstract:
This research was conducted with the aim of knowing the relationship or correlation between numerical abilities and verbal abilities of UPTD students at SMP Negeri 3 Sinjai. This study is a quantitative research with a research sample of 67 students. The sampling method used is Cluster Random Sampling. The data collection technique in this study used a numerical ability questionnaire and a verbal ability questionnaire. Data were analyzed by descriptive statistics and inferential statistics using correlation analysis. The results indicated that the average value of students' numerical ability was above the value of verbal ability, namely 68.05 for numerical ability and 55.68 for verbal ability, while based on the results of the calculation of correlation analysis techniques, the correlation coefficient value (r) was 0.33. The correlation of the two variables is in the weak category. These results suggest that there is a significant positive relationship between numerical ability and verbal ability. The higher the numerical ability, the higher the verbal ability. Conversely, the lower the numerical ability, the lower the verbal ability.
Published: 28 August 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 15-20; https://doi.org/10.31605/jomta.v4i1.1845

Abstract:
In this paper, we first discussed some results about multiplicative metric spaces to support the main results. The aim of this paper is to present fixed point some result that satisfied some generalized of contraction mapping related to multiplicative metric spaces. Furthermore, some examples are given to support results
, Oni Soesanto, Yuana Sukmawaty
Published: 28 August 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 1-7; https://doi.org/10.31605/jomta.v4i1.1757

Abstract:
Pada penelitian ini dilakukan uji simulasi data berskala besar sehingga diperlukan metode yang handal untuk permasalahan klasifikasi salah satunya adalah Radial Basis Function Neural Network (RBFNN). Untuk training data RBFNN menggunakan struktur khusus yang melibatkan dimensi tinggi pada hidden layer. Dengan struktur RBFNN yang khusus tersebut maka seringkali menimbulkan permasalahan karena hidden layernya terlalu besar, sehingga diperlukan penambahan metode penyederhaan jaringan seperti PCA dan K-Means Clustering. Metode PCA digunakan untuk mereduksi dimensi input pada RBFNN sedangkan metode K-Means Clustering digunakan untuk penentuan inisialisasi center awal pada RBFNN. Pada hasil percobaan metode PCA dihasilkan komponen utama ke-1 dan ke-2 dengan masing-masing mewakili 55.2288% dan 27.3108% dari seluruh variabilitas, secara kumulatif kedua komponen utama menyatakan sebesar 82.5396% dan hasil percobaan perulangan iterasi di metode penelitian ini didapatkan hasil rata-rata proses akurasi PC dan Klas terbaik berada pada PC-2 Klas-3 dengan akurasi di atas 90% untuk proses training dan testing dengan akurasi kesalahan klasifikasi di bawah 10%.
Nurjanna Nurjanna, Darma Ekawati, Fardinah Fardinah
Published: 28 August 2022
Journal of Mathematics : Theory and Application, Volume 4, pp 8-14; https://doi.org/10.31605/jomta.v4i1.1858

Abstract:
Setiap pelaku usaha atau pelaku ekonomi pasti melakukan prinsip ekonomi yaitu dengan modal yang sedikit mampu menghasilkan keuntungan maksimal, mengakibatkan munculnya masalah optimasi meliputi meminimumkan biaya atau memaksimumkan keuntungan dengan kapasitas sumber daya yang ada. Penelitian ini bertujuan untuk mengetahui optimalisasi produk tenun sa’be Toko Mandar Sutera menggunakan algoritma Branch and Bound. Metode yang digunakan dalam penelitian ini adalah algoritma Branch and Bound. Dalam penelitian ini diambil 11 jenis sarung, yakni sapeq, sapeq bocoq, pucuk, kotak-kotak, burberry, bunga kaiyang, arjuna, kucing garong, sandeq, lontara, dan malolo. Upaya optimalisasi keuntungan produk tenun sa’be memiliki beberapa kendala, yaitu persedian, bahan baku, waktu pembutan, jumlah karyawan, dan kapasitas gudang. Solusi awal diperoleh dengan menggunakan metode simpleks. Apabila hasilnya bernilai non integer maka dilanjutkan dengan algoritma Branch and Bound untuk mendapatkan solusi yang integer. Berdasarkan hasil penelitian diperoleh bahwa untuk mengoptimalkan produk tenun sa’be dengan keuntungan maksimal, maka Toko Mandar Sutera memproduksi produk jenis sapeq sebanyak 2 buah, burberry sebanyak 2 buah dan lontara sebanyak 1 buah dengan keuntungan produksi sebesar Rp460.000,00 per bulan