No abstract

The ensemble consists of a single set of individually trained models, the predictions of which are combined when classifying new cases, in building a good classification model requires the diversity of a single model. The algorithm, logistic regression, support vector machine, random forest, and neural network are single models as alternative sources of diversity information. Previous research has shown that ensembles are more accurate than single models. Single model and modified ensemble bagging model are some of the techniques we will study in this paper. We experimented with the banking industry’s financial ratios. The results of his observations are: First, an ensemble is always more accurate than a single model. Second, we observe that modified ensemble bagging models show improved classification model performance on balanced datasets, as they can adjust behavior and make them more suitable for relatively small datasets. The accuracy rate is 97% in the bagging ensemble learning model, an increase in the accuracy level of up to 16% compared to other models that use unbalanced datasets.

ABSTRAKDalam upaya meningkatkan keselamatan angkutan laut dan penyeberangan, pemeriksaan harus dilaksanakan disetiap kapal pada umumnya. Tidak dapat dipungkiri bahwa kondisi sarana transportasi laut di Indonesia banyak yang berusia tua sehingga kemampuannya tergolong relatif rendah dalam memenuhi harapan pengguna jasa akan pelayanan yang baik dan memuaskan. Teknik analisis data yang digunakan dalam rangka kajian ini adalah analisis diskriptif kuantitatif yang digunakan untuk mengetahui sejauhmana regulator, awak kapal dan masyarakat mengetahui pemakaian, darurat bahaya, dan pengoperasian peralatan keselamatan kapal dalam mendukung keselamatan kapal dalam pelayaran pada kapal laut dan penyeberangan di Provinsi Maluku.Pengguna kapal secara keseluruhan di Provinsi Maluku terhadap kontribusi persepsi masyarakat terhadap peralatan keselamatan kapal berpendapat bahwa pentingnya penempatan alat-alat keselamatan kapal sebesar 42%, ketersediaan perlengkapan penyelamat jiwa/ life saving appliances sebesar 30%, ketersediaan alat keselamatan yang ada di kapal sebesar 12%, ketersediaan data pendukung keselamatan kapal (dokumen) sebesar 16%, dan upaya peningkatan pelayanan keselamatan kapal khususnya di wilayah Maluku sebesar 0%.Pengguna kapal secara keseluruhan di Provinsi Maluku, kontribusi persepsi masyarakat terhadap peningkatan keselamatan kapal berpendapat bahwa komitmen peningkatan alat-alat keselamatan kapal sebesar 7%, SDM yang mengelola dan maintenance perlengkapan penyelamat jiwa/ life saving appliances sebesar 14%, ketersediaan peralatan keselamatan yang ada di kapal sebesar 14%, kelembagaan yang mengawasi ketersediaan peralatan keselamatan kapal sebesar 28%, lingkungan kapal sebagi upaya meningkatkan pelayanan keselamatan kapal khususnya di wilayah Maluku sebesar 15%, dan mobilitas peralatan keselamatan kapal sebesar 22%. ABSTRACTIn an effort to improve the safety of sea transport and crossing, the examination must be carried out on each vesselin general. It is inevitable that the conditions of sea transportation in Indonesia, many age old are relatively low, so its ability to meet the expectations of service users would be a good service and satisfying. Data analysis techniques used in the framework of this study is a descriptive analysis of quantitative used to determine the extent of the regulator, the crewand the public informed of the use, emergency danger, and the operation of safety equipment aboard in support of the safety of the ship in the cruise on ships and crossing in Maluku province. Users vessel overall in Maluku province to contribute the public perception of the safety equipment aboard argued that the importance of the placement of safety equipment aboard by 42%, the availability of supplies life-saving/ life saving appliances by 30%, the availability of safety equipment on board 12%, the availability of data supporting the safety of the ship (documents) by 16%, and improving the safety of the ship services, especially in Maluku region at 0%. Users vessel overall in Maluku province, the contributi...

This paper focuses on the study of a bankruptcy prediction model using a hybrid machine learning that combines two synergistic algorithms i.e. two-class boosted decision tree and multi-class decision forest. The hybrid model ensures the building of multiple decision trees whereby the latest tree corrects the previous tree, learning from the tagged data and subsequently votes on the most popular tree as the final decision of the ensemble. This hybrid machine learning is proposed to be an alternative of the bankruptcy prediction models that is able to produce three major classifications i.e. bankruptcy, grey area, and non-bankruptcy. There are five variables considered in the hybrid model which consist of working capital for total assets, retained by total asset, earnings before interest and taxes on total asset, market value of equity to total bank value of liabilities and sales of total asset. These input data are applied and tested to the public dataset produced by Bank Indonesia from year 2011-2015. The hybrid model shows a significant result whereby the overall area under curve (AUC) had successfully achieved 95% value that indicates the capability of the hybrid model to train the test data and identify the relationship of input-output data. This finding suggests that the machine learning approach can be treated as an alternative tool to build a bankruptcy prediction model for banking industry. Introduction

No abstract