p-Index From 2021 - 2026
16.274
P-Index
Claim Missing Document
Check
Articles

Comparison of Adaboost Application to C4.5 and C5.0 Algorithms in Student Graduation Classification Yuveinsiana Crismayella; Neva Satyahadewi; Hendra Perdana
Pattimura International Journal of Mathematics (PIJMath) Vol 2 No 1 (2023): Pattimura International Journal of Mathematics (PIJMath)
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/pijmathvol2iss1pp07-16

Abstract

Students become a benchmark used to assess quality and evaluate college learning plans. Therefore, students who graduate not on time can have an effect on accreditation assessment. The characteristics of students who graduate on time or not on time in determining student graduation can be analyzed using classification techniques in data mining, namely the C4.5 and C5.0 algorithms. The purpose of this study is to compare the application of the Adaboost Algorithm to the C4.5 and C5.0 Algorithms in the classification of student graduation. The data used is the graduation data of students of the Statistics Study Program at Tanjungpura University Period I of the 2017/2018 Academic Year to Period II of the 2022/2023 Academic Year. The analysis begins by calculating the entropy, gain and gain ratio values. After that, each data was given the same initial weight and iterated 100 times. Based on the classification results using the C5.0 Algorithm, the attribute that has the highest gain ratio value is school accreditation, meaning that the school accreditation attribute has the most influence in the classification of student graduation. The application of the Adaboost Algorithm to the C5.0 Algorithm is better than the C4.5 Algorithm in classifying the graduation of students of the Untan Statistics Study Program. The Adaboost algorithm was able to increase the accuracy of the C5.0 Algorithm by 12.14%. While in the C4.5 Algorithm, the Adaboost Algorithm increases accuracy by 10.71%.
Determination of the Annual Pension Fund Premium for Joint-Life Status Using the Aggregate Cost Method Syuradi syuradi; Neva Satyahadewi; Hendra Perdana
Pattimura International Journal of Mathematics (PIJMath) Vol 2 No 2 (2023): Pattimura International Journal of Mathematics (PIJMath)
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/pijmathvol2iss2pp71-78

Abstract

A pension fund is one of the responsibilities of an institution or company for all employees during their working life. In pension fund insurance, several agreements must be agreed upon by the insured and the insurer for the agreement, namely the premium. The premium to be paid by the insured (employee) of the pension fund insurance must adjust to the income earned, so that the premium to pay does not burden the insured. This study aims to determine the annual pension fund premium amount that must pay use the Aggregate Cost method in the joint-life case. The case study uses information from a husband and wife as civil servants with a husband class III B and wife III A participating in a pension program with a retirement age limit of 58 years (r = 58). The husband (insured x) was 28 years old, and the wife (insured y) was 24 when they started working and joined the pension program. The result of calculating the value of the annual pension fund insurance premium that must pay use the Aggregate Cost method is Rp.41,440,163. If the husband's age is lower than the wife's (x=24, y=28), then the value of the premium paid is more significant than when the husband's age is higher than the wife's (x=28, y=24), which is IDR 41,594,217. That is because the husband's working period is more extended than the wife's, while the chance of death for men is higher than for women. Meanwhile, premiums producing if the husband and wife are of the same age, which is cheaper than when the husband and wife are of different ages
Factor Analysis on Poverty in Kalimantan Island with Geographically Weighted Negative Binomial Regression Alvin Octavianus Halim; Neva Satyahadewi; Preatin Preatin
Pattimura International Journal of Mathematics (PIJMath) Vol 4 No 1 (2025): Pattimura International Journal of Mathematics (PIJMath)
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/pijmathvol4iss1pp41-52

Abstract

Poverty is one of the problems still faced by Indonesia. The problem of poverty is a development priority because poverty is a complex and multidimensional problem. Therefore, to reduce poverty, it is necessary to know the factors that influence the number of people living in poverty. The influencing factors in each region are different due to the effects of spatial heterogeneity between regions such as geographical, economic, and socio-cultural conditions. This research considers spatial factors by using the Geographically Weighted Negative Binomial Regression (GWNBR) method on poverty-based regions in Kalimantan Island. This research uses eleven independent variables. The weighting function used is the Adaptive gaussian kernel because the adaptive kernel can produce the number of weights that adjust to the distribution of observations. The stage starts with descriptive statistics and checking multicollinearity. Then proceed with the formation of Poisson Regression, because the data used is enumerated data. Then check for overdispersion. If overdispersion is detected where the variance is bigger than the mean, then Negative Binomial Regression is continued. After that, it is tested for the presence or absence of spatial heterogeneity. If there is, proceed to find the bandwidth and Euclidean distance. After that, the graphical weighting matrix is searched. Then proceed with GWNBR modeling. The results of the analysis show that there are seven significant variables, including the percentage of households with the main source of lighting is non-state electricity company (PLN), average monthly net income of informal workers, population density for every square kilometer, monthly per capita expense on food and non-food essentials, percentage of people who have a health complaint and do not treat it because there is no money and percentage of population 15 years and above who do not have a diploma. Based on the categories of significant variables, six groups were formed in 56 districts/cities in Kalimantan Island.
Cayenne Pepper Price Forecast in Singkawang City Based on Rainfall using Transfer Function Model Citra Cipta Maharani; Yundari Yundari; Neva Satyahadewi
Pattimura International Journal of Mathematics (PIJMath) Vol 4 No 2 (2025): Pattimura International Journal of Mathematics (PIJMath)
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/pijmathvol4iss2pp53-62

Abstract

Fluctuations in the price of cayenne pepper are a significant problem in Indonesia’s agricultural sector, especially in Singkawang City. Weather conditions, including rainfall are often the main factor affecting the production and distribution of cayenne pepper, causing price instability. This study aims to analyze the relationship between rainfall and the price of cayenne pepper, and build a forecasting model using a transfer function approach. In this study, the input series used is rainfall, while the output series is the price of cayenne pepper. The data used is secondary data obtained from the Central Statistics Agency in Singkawang City from January 2016 to December 2023. The data is analyzed through the stationarity stage, then the identification of the ARIMA model for the input series. After that, prewhitening and cross-correlation analysis were carried out to identify the parameter values and determine the noise series ARMA model. The results show that the transfer function model with parameters with ARMA noise series is the best model for forecasting the price of cayenne pepper. The results of forecasting the price of cayenne pepper in Singkawang City have a MAPE value of , so it can be concluded that the transfer function model is quite good at forecasting the price of cayenne pepper in Singkawang City with the highest forecasting result of IDR 61,899 in May 2024 and the lowest is IDR 32,206 in April 2024. This study focuses solely on the transfer function model because it is specifically designed to analyze the dynamic relationship between an input variable (rainfall) and an output variable (price). Other forecasting methods such as ARIMA or exponential smoothing only capture internal patterns within a single series and cannot represent the influence of external factors. Therefore, the transfer function approach is considered more appropriate for the purpose of this study.
Forecasting the Stock Price of PT. Dayamitra Telekomunikasi with Single Input Transfer Function Model Resti Arsanti; Neva Satyahadewi; Shantika Martha
Pattimura International Journal of Mathematics (PIJMath) Vol 4 No 2 (2025): Pattimura International Journal of Mathematics (PIJMath)
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/pijmathvol4iss2pp87-96

Abstract

The unpredictable movement of stock prices is often a challenge for investors, so it requires a deeper understanding and consideration of various factors before making investment decisions. One of the factors that affect stock price movements is trading volume. Therefore, this study uses a single input transfer function model to forecast the daily closing stock price of PT. Dayamitra Telekomunikasi, with the closing stock price as the output variable and the stock trading volume as the input variable. The transfer function is a forecasting model that integrates ARIMA with multiple regression analysis, allowing modeling not only based on the values of the output variables, but also considering the influence of the input variables. ARIMA model estimation is performed on the input series for the prewhitening process, then the order of the transfer function is determined using cross-correlation plots, as well as model diagnostic tests to ensure its feasibility. Model accuracy is calculated to evaluate its performance in forecasting. The data used in this study are daily data from the period July 5, 2022 to October 9, 2024. The transfer function model obtained has an order of (2,0,0), with a MAPE value of 1.09%, which indicates that the model has good accuracy. Based on the forecasting results, it is estimated that there will be a decrease in the share price of PT. Dayamitra Telekomunikasi Tbk for the next five periods
Comparison of Single Net Premium of Unit Linked Endowment Life Insurance using Annual Ratchet Method and Black Scholes Model Leona Idilla; Neva Satyahadewi; Shantika Martha
Pattimura International Journal of Mathematics (PIJMath) Vol 4 No 2 (2025): Pattimura International Journal of Mathematics (PIJMath)
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/pijmathvol4iss2pp73-86

Abstract

Annual Ratchet is an indexing method. Black Scholes is a model used to determine option. The purpose of this study is to compare the results of single net premium of unit-linked endowment life insurance using the Annual Ratchet method and the Black Scholes Model. The data used in this study are data on the daily closing share price of PT Telkom Indonesia (Persero) Tbk for the period December 20, 2021 to December 20, 2022, Bank Indonesia interest rates and the 2019 Mortality Table. In this study, a comparison is made between the Annual Ratchet method and the Black-Scholes model to calculate the net single premium of unit-linked endowment life insurance for a 30-year-old male insured. The results show that the premium calculated using the Annual Ratchet method is greater than the premium from the Black-Scholes model, which is Rp 8,725,000. This is due to the additional protection feature in the Annual Ratchet method, which provides a minimum guaranteed investment value, thus increasing the premium value to be paid.
ANALISIS KEMISKINAN DI INDONESIA DENGAN PENDEKATAN PANEL DINAMIS SYSTEM GENERALIZED METHOD OF MOMENTS Syahida, Murni; Martha, Shantika; Satyahadewi, Neva
BIMASTER : Buletin Ilmiah Matematika, Statistika dan Terapannya Vol. 15 No. 1 (2026): Bimaster : Buletin Ilmiah Matematika, Statistika dan Terapannya
Publisher : Faculty of Mathematics and Natural Sciences Tanjungpura University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Kemiskinan merupakan masalah multidimensional yang memengaruhi berbagai aspek kehidupan seperti kondisi sosial ekonomi, pendidikan, kesehatan, hingga kestabilan politik. Penelitian ini bertujuan membentuk model panel dinamis dalam mengidentifikasi faktor penentu tingkat kemiskinan di Indonesia melalui pendekatan estimasi System Generalized Method of Moments (System GMM) serta mengetahui pengaruh jangka pendek dan jangka panjang dari variabel-variabel yang digunakan. Penelitian ini mengolah data yang diperoleh dari Badan Pusat Statistik mencakup 34 provinsi di Indonesia selama periode 2015 hingga 2024. Proses analisis dimulai dengan analisis deskriptif untuk memberikan gambaran umum data, kemudian dilanjutkan dengan penyusunan model dan estimasi model panel dinamis menggunakan System GMM. Selanjutnya, dilakukan uji signifikansi parameter secara bersama-sama menggunakan uji Wald, sedangkan secara individual dilakukan dengan uji . Validitas model diuji melalui uji Sargan dan deteksi autokorelasi error dilakukan dengan uji Arellano-Bond. Berdasarkan model yang telah dibentuk dari hasil estimasi, didapatkan bahwa lag kemiskinan, variabel akses air minum layak, indeks pembangunan manusia serta rata-rata lama sekolah memiliki pengaruh positif dan signifikan terhadap kemiskinan. Hasil perhitungan menunjukkan variabel akses air minum layak, tingkat pengangguran terbuka, dan indeks pembangunan manusia memiliki pengaruh positif baik dalam jangka pendek dan jangka panjang.
OPTIMASI MULTI OBJEKTIF DAN ANALISIS PEMBENTUKAN PORTOFOLIO SAHAM JAKARTA ISLAMIC INDEX (JII) MENGGUNAKAN METODE NADIR COMPROMISE PROGRAMMING (NCP) Khairina Auliannisa; Evy Sulistianingsih; Neva Satyahadewi
Epsilon: Jurnal Matematika Murni dan Terapan Vol 19, No 1 (2025)
Publisher : Mathematics Study Program, Faculty of Mathematics and Natural Sciences, Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/epsilon.v19i1.14198

Abstract

Multi-objective problems involve multiple objective functions to solve complex problems, and the Nadir Compromise Programming (NCP) method is one way to solve these problems. These problems. Compared to other multi-objective methods, the NCP method has several advantages. Firstly, the weighting in the NCP method can utilize specific parameters to produce an effective optimal portfolio. Additionally, the optimum value of the risk coefficient can be achieved, thereby minimizing large losses. Achieved so as not to cause significant losses. When investing, several essential things need to be considered to achieve an optimal portfolio. These objectives include reducing risk, increasing potential returns, and reducing the amount of capital invested. This study aims to examine the application of the NCP method in solving multi-objective optimization problems for stock portfolios, utilizing monthly stock closing prices from May 2019 to May 2023. In this analysis, the monthly closing prices of 30 stocks that are members of the JII index are analyzed. Six stocks with positive expected returns and the highest stock ratio were selected to form the optimal portfolio. The stocks are BRIS and SIDO. The solution to this multi-objective problem indicates the proportion of funds allocated to the two stocks: BRIS, with a proportion of 0.341147, and SIDO, with a proportion of 0.658853. The analysis also shows that the optimal risk coefficient is 1, the maximum expected return is 0.014569, and the minimum investment capital is Rp.1067.
ANALISIS CONDITIONAL VALUE AT RISK PORTOFOLIO SAHAM DENGAN COPULA CLAYTON Sela Karlina; Evy Sulistianingsih; Neva Satyahadewi
EPSILON: JURNAL MATEMATIKA MURNI DAN TERAPAN Vol 18, No 2 (2024)
Publisher : Mathematics Study Program, Faculty of Mathematics and Natural Sciences, Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/epsilon.v18i2.13261

Abstract

Conditional Value at Risk (CVaR) is known as a risk measurement tool to estimate losses in investing. Financial data tends not to be normally distributed so that the flexible Copula method can be used to analyze financial data without requiring the assumption of normality. This study aims to analyze the CVaR of a stock portfolio with Clayton's Copula. The study began with collecting daily stock closing price data for the period October 3, 2022 to November 3, 2023. After the data was collected, the return value of the closing stock price was calculated. Furthermore, autocorrelation and heteroscedasticity tests were carried out on the closing stock price return data. Then, the Kendall's Tau correlation was calculated to obtain the Clayton Copula parameters. After that, the stock weights in the portfolio were calculated using the Mean Variance Efficient Portfolio (MVEP) method and new return data was generated using the Clayton Copula parameters. Furthermore, the portfolio return was calculated to obtain the VaR value of the formed portfolio. Then, it was repeated by generating data up to the VaR calculation 1000 times to obtain the average value of the portfolio VaR. Then, the same thing was done to CVaR. The results of the CVaR analysis of the stock portfolio with Copula Clayton on the two stocks, namely PT Aneka Tambang Tbk (ANTM) and PT Timah Tbk (TINS), obtained losses of 3.04%, 3.56%, and 4.57% with a confidence level of 90%, 95%, and 99%. This value indicates the percentage of investment risk that may be obtained in the next one-day period. This shows that the higher the level of confidence, the greater the CVaR value will be.
ANALISIS PERPINDAHAN STATUS KUALITAS UDARA BERDASARKAN KONSENTRASI PM2.5 DENGAN CONTINUOUS-TIME MARKOV CHAIN (CTMC) Septiani, Thara Amalia; Martha, Shantika; Satyahadewi, Neva
BIMASTER : Buletin Ilmiah Matematika, Statistika dan Terapannya Vol. 15 No. 2 (2026): Bimaster : Buletin Ilmiah Matematika, Statistika dan Terapannya
Publisher : Faculty of Mathematics and Natural Sciences Tanjungpura University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Kualitas udara merupakan faktor lingkungan yang berpengaruh terhadap kesehatan masyarakat, khususnya yang berkaitan dengan konsentrasi partikel halus PM2.5. Status kualitas udara dapat berubah dari waktu ke waktu sehingga diperlukan pendekatan analisis yang mampu menggambarkan pola perpindahan status tersebut secara probabilistik. Penelitian ini bertujuan untuk menganalisis karakteristik perpindahan status kualitas udara PM2.5 serta mengestimasi probabilitas transisi dan ekspektasi waktu bertahan setiap status kualitas udara menggunakan pendekatan Continuous-Time Markov Chain (CTMC). Data yang digunakan berupa data konsentrasi PM2.5 per jam yang diperoleh dari Badan Meteorologi, Klimatologi, dan Geofisika (BMKG) Stasiun Meteorologi Kelas l Supadio pada periode Agustus hingga Oktober 2025. Konsentrasi PM2.5 diklasifikasikan ke dalam status kualitas udara berdasarkan Indeks Standar Pencemar Udara (ISPU), kemudian dibentuk transisi antarstatus berdasarkan urutan pengamatan per jam. Parameter model CTMC berupa matriks generator (Q-matrix) diestimasi menggunakan metode Maximum Likelihood Estimation. Hasil analisis menunjukkan bahwa status baik memiliki ekspektasi waktu bertahan paling lama, yaitu sekitar 6,41 jam, diikuti status sedang sekitar 3,29 jam, sedangkan status tidak sehat memiliki waktu bertahan paling singkat, yaitu sekitar 1,76 jam. Distribusi steady-state menunjukkan bahwa dalam jangka panjang kualitas udara cenderung berada pada status baik dengan probabilitas sekitar 63,38%, diikuti status sedang sebesar 34,66%, sementara status tidak sehat memiliki probabilitas yang relatif kecil. Pola probabilitas transisi dalam interval satu jam menunjukkan bahwa perubahan status kualitas udara umumnya terjadi secara bertahap.
Co-Authors . Apriansyah Aditya Handayani Afghani Jayuska Afghany Jayuska Alqadri, Syarifah Putri Tasya Vahira Alvin Octavianus Halim Amriani Amir Amriani Amir Amriani Amir Andani, Wirda Annisa Auliarahmi Antoni, Frans Xavier Natalius Apriliyanti, Rita Aprizkiyandari, Siti Ardhitha, Tiffany Ari Hepi Yanti Arsyi, Fritzgerald Muhammad Arti, Reyana Hilda Ashari, Asri Mulya Asri Mulya Ashari Asty Fistia Ningrum Atikasari, Awang Aulia Nabila Putri Aulia Puteri Amari Banu, Syarifah Syahr ciptadi, wahyudin Citra Cipta Maharani Cornellia, Amanda Dadan Kusnandar Dadan Kusnandar Dadan Kusnandar David Jordy Dhandio Debataraja, Naomi Nessyana Della Zaria Desriani Lestari Desriani Lestari Desriani Lestari Dhandio, David Jordy Dinda Lestari Dwi Nining Indrasari Dwinanda, Maria Welita Eka Febrianti, Eka Esta Br Tarigan Evy Sulistianingsih Ewaldus Okta Febrant Alfariz Ferdina Ferdina Feriliani Maria Nani Fitriawan, Della Fransisca Febrianti Sundari Fransiska Fransiska Grikus Romi Gusti Eva Tavita Gusti Eva Tavita Hairil Al-Ham Hamzah, Erwin Rizal Hanin, Noerul Harimurti, Puspito Harnanta, Nabila Izza Helena, Shifa Hendra Perdana Hendrianto, El Herina Marlisa Huda, Nur'ainul Miftahul Huriyah, Syifa Khansa Ibnur Rusi Ikha Safitri Ilhan Nail Nabil Imro'ah, Nurfitri IMRO’AH, NURFITRI Imtiyaz, Widad Isra’ Sagita Jawani Jawani Jessica Audrey Valeria Khairina Auliannisa Kusnandar, Dadan Tonny Leona Idilla Louis Putra Jaya Lucky Hartanti Lucky Hartanti Lucky Hartanti M. Deny Hafizzul Muttaqin Maga, Fahmi Giovani Margareta, Tiara Margaretha, Ledy Claudia Marlisa, Herina Marola, Geby Martha, Shantika Maulidya, Gita Arinda Mega Sari Juane Sofiana Mega Sari Juane Sofiana Mega Tri Junika Millennia Taraly Misrawi Misrawi Muhammad Ahyar Muhammad Fikri Muhammad Radhi Muhammad Rizki Muliadi Muliadi Muliadiasti, Maresha Widya Muslimah (F54210032) Nabil, Ilhan Nail Nanda Shalsadilla Naomi Nessyana Debataraja Naomi Nessyana Debataraja Nazwa Nursyifa Nirwani Noerul Hanin Nona Lusia Novi Novi Nugrahaeni, Indah Nur Asih Kurniawati Nur Asiska Nurfadilah, Kori’ah Nurfitri Imro'ah Nurfitri Imro’ah Nurhalita Nurhalita Nurmaulia Ningsih Oktaviani, Indah Ovi Indah Afriani Paisal Paisal Pertiwi, Retno Pitriani Pratama, Aditya Nugraha Preatin Preatin Putri Putri Qalbi Aliklas R Puspito Harimurti Radhi, Muhammad Radinasari, Nur Ismi Rafdinal Rafdinal Rahadi Ramlan Rahmadanti, Putri Rahmanita Febrianti Rusmaningtyas Rahmawati, Fenti Nurdiana Ramadhan, Nanda Ramadhania, Wahida Regita, Luna Amara Reni Unaeni Resti Arsanti Retnani, Hani Dwi Ria Andini Ria Fuji Astuti Rina Rina Risky Oprasianti Rita Kurnia Apindiati Rivaldo, Rendi Riza Linda Rizki Nur Rahmalita Rizki, Setyo Wira Rosi Kismonika Roslina Rosi Tamara Rovi Christova Safira, Shafa Alya Salsabilla, Arla Santika Santika Sary, Rifkah Alfiyyah Savitri, Dini Dwi Seftiani, Seftiani Sela Karlina Selvy Putri Agustianto Septiani, Thara Amalia Setyo Wir Rizki Setyo Wira Rizki Setyo Wira Rizki Setyo Wira Rizki Shantika Martha Shantika Martha Sinaga, Steven Jansen Sintia Margun Sista, Sekar Aulia Siti Aprizkiyandari Siti Aprizkiyandari, Nurul Qomariyah, Shantika Martha, Siti Hardianti Suci Angriani Sukal Minsas Sukal Minsas Syahida, Murni Syuradi syuradi Tamtama, Ray Taraly, Inggriani Millennia Tiara, Dinda Trifaiza, Fadhela Wahyu Diyan Ramadana Wahyudin Ciptadi Warsidah Warsidah Wilda Ariani Wirda Andani Wirda Andani Yohanna Gabriel Richsita Yopi Saputra Yudhi Yuliono, Agus Yumna Siska Fitriyani Yundari Yundari Yundari, Yundari Yuveinsiana Crismayella Yuyun Eka Pratiwi Zakiah, Ainun