High volatility is a major problem in generating accurate predictions of stock prices. It also causes unstable predictions and increases the loss risk. Therefore, an adaptive prediction model that is able to adjust to dynamic data pattern changes is needed. This study aims to address these issues by developing an Extreme Gradient Boosting (XGBoost) model optimized using Adaptive Particle Swarm Optimization (APSO). XGBoost was chosen for its ability to handle nonlinear relationships and minimize overfitting, while APSO serves to adaptively adjust parameters to obtain the optimal combination of hyperparameters. The novelty of this research lies in the application of XGBoost-APSO integration in the context of stock price prediction in the Indonesian capital market, which is characterized by high volatility. The study was conducted using daily closing price data of PT Aneka Tambang Tbk (ANTM) shares from November 2020 to May 2025 to predict prices seven days ahead. The results show that the XGBoost-APSO model provides the best performance with a MAPE value of 0.2%, superior to XGBoost-PSO (2.58%) and standard XGBoost (2.91%). This approach effectively improves prediction accuracy and supports quick and accurate investment decision making, while contributing to the development of intelligent prediction systems in the Indonesian capital market.

The banking industry faces significant challenges in retaining customers, as churn can critically affect both revenue and reputation. This study introduces a robust churn prediction framework by comparing the performance of XGBoost and Random Forest algorithms under imbalanced data conditions. The novelty of this research lies in integrating the SMOTE and SMOTE-ENN techniques with machine learning algorithms to enhance model performance and reliability on highly imbalanced datasets. Unlike conventional approaches that rely solely on oversampling or undersampling, this study demonstrates that the hybrid combination of XGBoost and SMOTE provides superior predictive accuracy, stability, and efficiency. Hyperparameter optimization using GridSearchCV was conducted to identify the most effective parameter configurations for both algorithms. Model performance was evaluated using the F1-Score and Area Under the Curve (AUC). The results indicate that XGBoost with SMOTE achieved the best performance, with an F1-Score of 0.8730 and an AUC of 0.9828, showing an optimal balance between precision and recall. Feature importance analysis identified Months_Inactive_12_mon, Total_Trans_Amt, and Total_Relationship_Count as the most influential predictors. Overall, this approach outperforms traditional resampling and modeling techniques, providing practical insights for data-driven customer retention strategies in the banking industry.

Meta-analysis is a statistical method for synthesizing quantitative data from multiple related studies, yet heterogeneity among studies often complicates interpretation. Meta-regression extends this approach by incorporating study-level covariates to explain variations in outcomes. With the global increase in depression, Acceptance and Commitment Therapy(ACT) has attracted attention as an effective psychological intervention. Therefore, a deeper understanding of the factors that influence its effectiveness across studies is needed. However, to date, only a few meta-analyses have quantitatively examined moderator variables that influence ACT outcomes using a random effects meta-regression approach. This study aims to fill this gap. This study estimated the model parameters using the Weighted Least Squares (WLS) method. Thirty-three published studies testing the effectiveness of ACT in reducing depression were collected from PubMed, Google Scholar, and Science Direct. The homogeneity test results showed significant heterogeneity, supporting the use of a random effects model. The combined effect size of -0.321 indicates that ACT significantly reduces depression levels compared to the control group. Meta-regression analysis revealed that variation in effect size was significantly influenced by differences in the average age of patients and duration of therapy. These findings provide new insights into the conditions and characteristics that make ACT therapy more effective.

Crime in Indonesia has shown a fluctuating trend and has increased significantly in recent years, with striking variations in crime rates between provinces. This phenomenon raises questions about the role of socio-economic factors such as education, poverty, and unemployment in influencing crime rates. Although there have been many studies examining the relationship between these variables and crime, the approaches used often assume that the relationship between variables is homogeneous across regions. In fact, heterogeneity in characteristics between provinces can cause different relationships. Therefore, an analysis approach is needed that can accommodate this diversity. This study proposes the Fuzzy Clusterwise Regression method which not only improves model accuracy compared to classical linear regression (with an increase in the coefficient of determination from 65.72% to more than 90%), but is also able to identify different patterns of relationships between regional groups (clusters). The results from FCR showed that the effect of socio-economic factors on crime varies between clusters and the optimum number of clusters is 4. In cluster 1, cluster 2, and cluster 3 all the variables had a significant influence on the amount of crime. Meanwhile, in cluster 4, the population poverty variable has no significant effect on the crime rate.

One of the models in survival analysis is the Cox proportional hazards model. This method ignores assumptions regarding the distribution of survival times studied. If there are indications of multicollinearity in data handling, one way that can be done is to use PCA (Principal Component Analysis). PCA-Cox regression is a combination of survival analysis and PCA which can be an alternative in analyzing multicollinearity survival data. The large number of cases of bad credit means that customers must be careful in providing credit to prospective customers. Character, capacity, capital and collateral variables are thought to influence the length of time customers pay house ownership loans at the bank. The data used is secondary data (n=100) regarding the assessment of character variables, capacity, capital and collateral, credit collectibility, and time to pay customer house ownership loans at the bank. The results of the analysis using PCA-Cox regression show that the variables character, capacity, capital and collateral have a significant effect on the length of house ownership loan payment time for Bank X customers. The originality of this research is the use of the PCA-Cox regression integration model in bank credit risk analysis.

PT Perkebunan Nusantara VIII (PTPN VIII) is a State-Owned Enterprise (BUMN). It operates in the plantation sector. The leading commodity is tea. The demand for tea produced by PTPN VIII is increasing. Thus, planning tea production is necessary. One of the production planning efforts is through forecasting based on previous data. Tea production data is time-series data. It contains seasonal elements and is dependent on other locations. We will analyze data with these criteria using space-time models, one of which is vector autoregressive (VAR). VAR models the relationship between observations on certain variables at one time. It also models the observation of the variable itself at previous times. Additionally, VAR models the relationship between observations and other variables at previous times. This paper explains how to forecast tea production. It uses the reconstituted VAR and Seasonal Autoregressive Moving Average (SARIMA) models. The results showed that the reconstituted VAR model was better than the SARIMA model in predicting tea production. The tea production prediction was at the Sedep and Santosa plantations in Bandung Regency.

This study examines the existence of breast cancer from the perspective of statistics as one alternative solution. From a statistical point of view, breast cancer management can be done with early detection and appropriate and fast treatment measures through diagnosis classification. In conducting early detection, an accurate diagnosis model is needed and can be developed by developing and testing statistical methods, one of which is the classification method. The classification methods used in this study are Support Vector Machine (SVM) and LightGBM. Both methods have a high level of classification accuracy because the algorithm used is robust and sensitive in determining each object in the classification member. Therefore, these two methods classify breast cancer into malignant and benign categories. The results of this study show that the best method to classify breast cancer is the SVM method, with an accuracy rate of 97.9%.

Spatial analysis of count data is important in epidemiology and other domains to identify spatial patterns. While Bayesian spatial models are a popular approach, they do require detailed knowledge of the process for model fitting, checking, and visualising results. Although a number of R packages are available to simplify running the model, there are still complexities when checking the model. This paper aims to provide a user-friendly and interactive R Shiny web application for the analysis of spatial data using Bayesian spatial Conditional Autoregressive Leroux models. The web application is built with the integration of the R packages shiny and CARBayes. The required data are the number of cases, population, and optionally some covariates for each region. In this case, we used Covid-19 data in 2021 in South Sulawesi province, Indonesia. This application enables fitting a Bayesian spatial CAR Leroux model under several hyperpriors and selecting the most appropriate through comparing several goodness of fit measures. The application also enables checking convergence, plus obtaining and visualising in an interactive map the relative risk of disease for each region.

Paraphrasing is a way to write sentences with other words with the same intent or purpose. Automatic paraphrase detection can be done using Natural Language Sentence Matching (NLSM) which is part of Natural Language Processing (NLP). NLP is a computational technique for processing text in general, while NLSM is used specifically to find the relationship between two sentences. With the development Neural Network (NN), nowadays NLP can be done more easily by computers. Many models for detecting and paraphrasing in English have been developed compared to Indonesian, which has less training data. This study proposes SPratama Model, which models paraphrase detection for Indonesian using a Recurrent Neural Network (RNN), namely Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU). The data used is "Quora Question Pairs" taken from Kaggle and translated into Indonesian using Google Translate. The results of this study indicate that the proposed model has an accuracy of around 80% for the detection of paraphrased sentences.

The manufacturing sector is considered a pivotal contributor to the growth of the economy around the globe. Kenya relies on the manufacturing sector to generate revenue and ultimately enhance the growth of the economy. Despite the key purpose played by these sectors in the economy, inflation rate has diversely affected their performance. The purpose of the study was to develop the Autoregressive Integrated Moving Average time series model to forecast the inflation rate in Kenya. The analysis utilized secondary data from the Kenya National Bureau of Statistics and the model was fitted to the data using R. The ARIMA with the information criterion of 576.24 was identified as the best model. Based on the forecasting, it was established that there will be a slight shift in the inflation in the coming years. Therefore, the government should use wage and price control to fight inflation but put in place policies to prevent recession and job loss in the country. The government should also employ contractionary monetary policy to fight inflation by reducing the money supply in the economy through decreases bond prices and increased interest rates. Implementation of these recommendations might assist in reducing the rate of inflation in the country.