cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dr. Muhammad Ahsan
Contact Email
muh.ahsan@its.ac.id
Phone
+6281331551312
Journal Mail Official
inferensi.statistika@its.ac.id
Editorial Address
Department of Statistics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember (ITS) Kampus ITS Keputih Sukolilo Surabaya Indonesia 60111
Location
Kota surabaya,
Jawa timur
INDONESIA
Inferensi
Published by Institut Teknologi Sepuluh Nopember Surabaya
ISSN : 0216308X     EISSN : 27213862     DOI : http://dx.doi.org/10.12962/j27213862
Core Subject : Science, Education, Social, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Engineering Mathematics Social Sciences
The aim of Inferensi is to publish original articles concerning statistical theories and novel applications in diverse research fields related to statistics and data science. The objective of papers should be to contribute to the understanding of the statistical methodology and/or to develop and improve statistical methods; any mathematical theory should be directed towards these aims; and any approach in data science. The kinds of contribution considered include descriptions of new methods of collecting or analysing data, with the underlying theory, an indication of the scope of application and preferably a real example. Also considered are comparisons, critical evaluations and new applications of existing methods, contributions to probability theory which have a clear practical bearing (including the formulation and analysis of stochastic models), statistical computation or simulation where the original methodology is involved and original contributions to the foundations of statistical science. It also sometimes publishes review and expository articles on specific topics, which are expected to bring valuable information for researchers interested in the fields selected. The journal contributes to broadening the coverage of statistics and data analysis in publishing articles based on innovative ideas. The journal is also unique in combining traditional statistical science and relatively new data science. All articles are refereed by experts.
Arjuna Subject : Matematika - Statistik dan Probabilitas
Articles 157 Documents
 12   13   14   15   16 
Comparison of Naïve Bayes and K-Nearest Neighbor (K-NN) Methods in Classifying Stunting in Toddlers in Takalar Regency Wahidah Sanusi; Irwan Thaha; Aliyah Arianti Halim
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9026

Abstract

Stunting is a chronic nutritional problem that has long-term effects on children's physical growth and cognitive development. Therefore, classifying the nutritional status of toddlers is an important step in early detection and determining appropriate interventions. This study aims to compare the performance of two classification methods, namely Gaussian Naïve Bayes and K-Nearest Neighbor (K-NN), in identifying the nutritional status of toddlers. The data used consisted of 14,620 toddler data obtained from the Takalar District Health Office covering 11 sub-districts. Gaussian Naïve Bayes is a probabilistic classification method with the assumption of independence between variables, while K-NN is a nonparametric method that classifies data based on the proximity of the distance between observations. The results showed that Gaussian Naïve Bayes produced an accuracy of 91.76%, but was unable to accurately classify stunting classes due to class imbalance and low posterior probability values in minority classes. In contrast, the K- NN method with an optimal parameter value of k=3 produced an accuracy of 97.00% and showed better performance in identifying toddlers with stunting status. Based on these results, the K-NN method is considered superior to Gaussian Naïve Bayes in classifying the nutritional status of toddlers in Takalar Regency.
Validating Analytical Derivatives for Enhanced Accuracy in Academic Score Modeling Anita Rahayu; Noryanti Muhammad
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9236

Abstract

The correct mathematical formulation and the determination of model that suit the characteristics of the data play crucial role in ensuring accurate modeling. Considering the various problems that exist today where complex mathematical formulations require advanced solutions, this study was conducted with the aim of testing the validity of analytical derivatives using relative differences and analysing the relationship between student academic achievement using the Generalized Linear Model (GLM). The initial stage of the study focused on testing the first derivative of the log-likelihood function for each estimated parameter. If the analytical derivative is correct, the next step is to analyse the regression relationship where the parameter estimation uses Maximum Likelihood Estimation (MLE). This study used secondary data from 40 students at University "X" in 2026, with final grades as the response variable; midterm and final exam, assignment, and self-study scores as predictor variables. The results showed that the relative differences for all parameters were equal to or close to zero, which means that the resulting analytical derivative was correct. Furthermore, analysis using GLM resulted in the conclusion that the estimated values were close to the actual values, so it can be said that the model has good accuracy and reliability.
A Comparative Study of Fuzzy Chain Ladder and Fuzzy Bornhuetter-Ferguson Methods for Claims Reserving Mujiati Dwi Kartikasari
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9449

Abstract

Accurate estimation of claim reserves is critical for the solvency of non-life insurance companies. Classical deterministic methods, such as Chain Ladder (CL) and Bornhuetter-Ferguson (BF), often fail to capture the inherent vagueness in actuarial judgments regarding development patterns and prior information. Fuzzy Set Theory, particularly through Triangular Fuzzy Numbers (TFNs), offers a formal framework to model this imprecision. This study conducts an empirical comparative analysis of two fuzzy reserving methods: the Fuzzy Chain Ladder (FCL) and the Fuzzy Bornhuetter-Ferguson (FBF). The FCL method fuzzifies the development factors, while the FBF method extends fuzzification to both the development pattern and the prior estimate of ultimate losses. Both methods are applied to a real-world liability insurance claims dataset from an Indonesian company, structured into a run-off triangle. The performance is evaluated by comparing the central reserve estimates, the total model uncertainty, and the asymmetry of the fuzzy output intervals. The results indicate that the FCL method produces a more conservative and volatile central reserve, approximately 12.3% higher than the FBF estimate under a risk-neutral assumption. More importantly, the FBF method demonstrates superior stability, with a total uncertainty measure about 14.7% lower than FCL, and exhibits an asymmetric uncertainty structure in which the right spread is consistently narrower, making its defuzzified reserve less sensitive to the actuary's risk attitude. The study concludes that the FCL method is suitable as a transparent, data-driven benchmark, whereas the FBF method is recommended for generating more robust and risk-sensitive forecasts when credible prior information is available.
Analyzing the Performance of Machine Learning Architectures in Predicting Padang's Precipitation Rahmat Hidayat
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9455

Abstract

This study evaluates the effectiveness of a machine learning approach for delivering precise daily rainfall forecasts in Padang City. The study aims to determine the most effective predictive model to support local decision-making and urban development, taking into account the considerable variability of precipitation patterns in the area. The methodology involves a comparative analysis of three prominent machine learning algorithms: Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost). Each model was meticulously evaluated using a comprehensive set of criteria, including accuracy, precision, recall, F1 score, and Area Under the Curve (AUC). The experimental findings indicate that all three models can forecast daily precipitation with considerable accuracy. The Random Forest model demonstrated superior performance within the group, achieving a peak prediction accuracy of 85%. The statistics demonstrate that the Random Forest model is the most dependable approach for forecasting precipitation events in Padang City. This model is highly recommended for integration into early warning systems and activity planning frameworks to mitigate the impacts of unpredictable weather in urban environments.
A Hybrid Semiparametric Regression Approach Using Truncated Spline–Wavelet Estimators for Modeling Nonstationary Financial Performance: Evidence from Village Credit Institutions in Bali Ni Putu Ayu Mirah Mariati; I Wayan Sudiarsa; Putu Diah Kumalasari
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9460

Abstract

This research proposes a novel semiparametric regression framework, integrating truncated spline and wavelet estimators in the modeling of dynamic relationships among CG, IC, and institutional performance in Bali's Village Credit Institutions (LPDs) in Indonesia. The robustness of this estimator is initially tested by a Monte Carlo simulation under various conditions of nonstationarity. From these, it becomes quite clear that the proposed hybrid spline-wavelet model has produced the least MSE (MSE = 0.0076) and greatest coefficient of determination (R² = 0.968). However, the specific penalized estimation method used ensures an appropriate bias variance tradeoff, allowing the proper modeling of global smooth trends and local short term variations. Latent CG and IC constructs obtained through Partial Least Squares Structural Equation Modeling were applied as covariates to the hybrid regression model by using a longitudinal database from 86 LPDs over the period 2016-2023. From the empirical findings, it was manifested that CG and IC significantly influence institutional performance and account for as much as 78% of its variation. The time varying component depicted three phases: reform growth from 2016 to 2019, the pandemic contraction in 2020-2021, and post recovery stabilization in 2022-2023. In general, this hybrid spline-wavelet estimator showed superior precision, decreasing MSE by up to 31% compared to single basis models, and provided a novel methodological contribution to nonstationary financial and econometric modeling.
Factors Affecting Interest in Revisiting Kare Tourism Village Based on Structural Equation Modeling M Fariz Fadillah Mardianto; Elly Pusporani; Suliyanto Suliyanto; Sri Endah Nurhidayati; Na’imatul Lu’lu’a; Marcelena Vicky Galena
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9951

Abstract

This research focuses on analyzing the factors that affect tourists' intentions to revisit Kare Tourism Village. Utilizing quantitative methods, primary data were gathered through questionnaires from 105 tourists who had previously visited the village. The SEM-PLS method was employed for analysis. In this study, several latent variables were identified, including facilities and services in Kare Tourism Village as exogenous latent variables, tourist satisfaction as both an endogenous latent variable and an intermediate variable, and tourist interest as the dependent variable. The findings reveal an value of 0.876 for tourist satisfaction, indicating that 87.6% of the variation in satisfaction can be explained by the model, which is considered strong. In contrast, the R² value for tourist interest is 0.548, suggesting that 54.8% of the variation in interest is explained by the model, classified as moderate. Additionally, the GoF value of 0.673 demonstrates a high model fit. Furthermore, the service variables in Kare Tourism Village significantly impact tourist satisfaction.
Prediction of USD Exchange Rate Against CNY and RUB Using Support Vector Regression and Neural Network M Fariz Fadillah Mardianto; Larisa Mutiara Putri; Evi Wijayawati; Sugha Faiz Al Maula Al Maula
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9952

Abstract

Major currency exchange rates have been impacted by the escalation of global trade volatility brought on by the trade war between the United States and China and economic sanctions imposed on Russia. USD dominance in global trade exposes developing countries to economic risks. BRICS seeks to reduce reliance by boosting local currency trade and diversifying reserves. This study analyzes BRICS exchange rate movements, specifically USD-RUB and USD-CNY, using Support Vector Regression (SVR) and Neural Network (NN). Statistical analysis of 2009-2025 data shows USD-RUB's high volatility due to oil prices and sanctions, while USD-CNY remains more stable but is influenced by monetary policy and global conditions. The results show that the SVR method is superior to NN in prediction accuracy. For USD-RUB, SVR with a sigmoid kernel achieves MSE 6.1596, MAE 1.8808, and MAPE 1.95%, while for USD-CNY, SVR with a Radial Basis Function kernel achieves MSE 0.0014, MAE 0.0322, and MAPE 0.45% Thus, the use of SVR-based prediction models is recommended to analyze the exchange rate to reduce the risk of volatility. Additionally, diversifying reserves, enhancing bilateral trade in local currencies, and considering external factors like commodity prices and global policies can improve exchange rate stability and economic resilience.

Page 16 of 16 | Total Record : 157

 12   13   14   15   16 

Filter by Year

2018 2026


Reset
Filter By Issues
All Issue Vol 9 No 1 (2026) Vol 8, No 3 (2025) Vol 8, No 2 (2025) Vol 8, No 1 (2025) Vol 7, No 3 (2024) Vol 7, No 2 (2024) Vol 7, No 1 (2024) Vol 6, No 2 (2023) Vol 6, No 1 (2023) Vol 5, No 2 (2022) Vol 5, No 1 (2022): Inferensi Special Issue: Seminar Nasional Statistika XI 2022 Vol 4, No 2 (2021): Inferensi Vol 4, No 1 (2021): Inferensi Vol 3, No 2 (2020): Inferensi Vol 3, No 1 (2020): Inferensi Vol 2, No 2 (2019): Inferensi Vol 2, No 1 (2019): Inferensi Vol 1, No 2 (2018): Inferensi Vol 1, No 1 (2018): Inferensi More Issue