Diabetes is a chronic disease that can cause serious illness. Women are four times more likely to develop heart problems caused by diabetes. Women are also more prone to experience complications due to diabetes, such as kidney problems, depression, and decreased vision quality. Nearly 200 million women worldwide are affected by diabetes, with two out of five affected by the disease being women of reproductive age. This paper aims to predict women with at least 21 years of age having diabetes based on eight diagnostic measurements using the statistical learning methods; Multinomial Naive Bayes, Fisher Discriminant Analysis, and Logistic Regression. Model validation is built based on dividing the data into training data and test data based on 5-fold cross-validation. The model validation performance shows that the Gaussian Naïve Bayes is the best method in predicting diabetes diagnosis. This paper’s contribution is that all performance measures of the Multinomial Naïve Bayes method have a value greater than 93 %. These results are beneficial in predicting diabetes status with the same explanatory variables.

This paper proposes support vector machines (SVMs), which is currently one of the most popular algorithms in machine learning (ML), in order to classify the low birth weight (LBW) data. The main objectives of this study are to predict the classification of LBW data in Indonesia based on the SVMs andto compare the performance of the proposed SVMs with the binary logistic regression as the most common model for classification of LBW data. The obtained samples were based on the results of Indonesian Demographic and Health Survey in 2012. The results showed that SVMs with four kernel functions (linear, radial, polynomial and hyperbolic tangent) were fit well to the LBW data in Indonesia. Furthermore, the constructed SVMs based on linear kernel function had the best performance among the SVMs with the other proposed kernel functions. This research also concluded that the SVMs based on linear kernel competed well with thebinary logistic regression forclassification LBW data in Indonesia.

This paper discussed about Calculation of joint life insurance premiums based on Gompertz mortality assumptions that affect the probability of joint insurance participants. One important variable in calculating premiums and reserves is interest rates. The foreign exchange rate is the price of a currency if exchanged with another countrys currency. Depreciation in the foreign exchange rate causes fluctuations in interest rates which ultimately affect the calculation of premiums for joint life insurance. Based on the calculation results, the greater the depreciation value, the greater the interest rate. This will increase risk for insurance companies. Calculation of insurance premiums that are affected by dollar fluctuations, is expected to be able to obtain calculations that are in accordance with the world economic trends.

Cervical cancer is one of the deadliest female cancers. Early identification of cervical cancer through pap smear cell image evaluation is one of the strategies to reduce cervical cancer cases. The classification methods that are often used are SVM, MLP, and K-NN. The weakness of the SVM method is that it is not efficient on large datasets. Meanwhile, in the MLP method, large amounts of data can increase the complexity of each layer, thereby affecting the duration of the weighting process. Moreover, the K-NN method is not efficient for data with a large number of attributes. The ensemble method is one of the techniques to overcome the limitations of a single classification method. The ensemble classification method combines the performance of several classification methods. This study proposes an ensemble method with the majority voting that can be used in cervical cancer classification based on pap smear images in the Herlev dataset. Majority Voting is used to integrate test results from the SVM, MLP, and KNN methods by looking at the majority results on the test data classification. The results of this study indicate that the accuracy results obtained in the ensemble method increased by 1.72% compared to the average accuracy value in SVM, MLP, and KNN. for sensitivity results, the results of the ensemble method were able to increase the sensitivity increase by 0.74% compared to the average of the three single classification methods. for specificity, the ensemble method can increase the specificity results by 3.4%. From the results of the study, it can be concluded that the ensemble method with the most votes is able to improve the classification performance of the single classification method in classifying cervical cancer abnormalities with pap smear images.

The results of the exploration of tracer study data can be used as information about the career of graduates and the relevance of work to the field of study as well as the competencies obtained before graduation. The question items discussed were a description of the time and process of looking for a job, the length of time to get the first job, the relationship between length of study, gender, field of work, total income, alumni's perception of the closeness of the field of study to work, the suitability of the level of education on the job, and average level of competence. The aim of this study was to analyze the relationship between these variables in the 2020 tracer study data from graduates of all faculties at Sriwijaya University. Respondents studied were 2,669 people. The method used is descriptive statistics, biplot analysis, independence test and plots by simple correspondence analysis. Respondents' perceptions of the suitability of the level of education in employment are related to gender and also with respondents' perceptions of the closeness of the field of study to the field of work. Meanwhile, respondents' perceptions of the closeness of the field of study with work are related to the field of work. The average length of study, the average number of job applications, the number of companies or agencies that responded to applications, and invited interviews for female respondents were lower than male respondents.