Ensemble machine learning algorithm optimization of bankruptcy prediction of bank

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.

Optimization of Multi-Layer Perceptron in Ensemble Using Random Search for Bankruptcy Prediction

“…Table 2 that the effectiveness of the proposed solution can also be found in other work, such as using PSO and CSO hyperparameter optimization based on majority vote ensembles (Safi et al, 2022) or applying optimization of machine learning algorithms to predict bank bankruptcy (Siswoyo et al, 2022).…”

“…Our aim is to create a reliable classification model to help businesses, identify financial ratio, including crisis, uncertainty, and stability. In addition, we first made literary observations related to our earlier work (Altman, 2013;Abdullah, 2021;Pisula, 2020;Siswoyo et al, 2022;Safi et al, 2022) The banking ratio finance dataset is what we use to train and test the hyperparameters of our multilayer perceptron when it is used to predict bankruptcy.…”

“…One of the most active fields in recent times, bankruptcy prediction analysis utilizing ensemble learning, has seen an increase in research activity year after year (Barboza et al, 2017;Faris et al, 2020;Siswoyo et al, 2022) The overarching purpose of this research is to develop a reliable system for predicting bankruptcies. For a good reason, many researchers have concentrated on the problem of bankruptcy prediction.…”

Comparison of ensemble hybrid sampling with bagging and boosting machine learning approach for imbalanced data

“…In other words, accuracy will not give a clear picture of the classifier's performance in an imbalanced dataset. Issues of imbalanced data occurred in many fields such as bankruptcy risk data [2], credit scoring [3], healthcare medical data [4], student performance [5], point cloud data [6], anomalies detection [7] and also water quality data [8]. In real-world applications, the severity of class imbalance may range from mild to severe [9].…”

A prediction model based machine learning algorithms with feature selection approaches over imbalanced dataset

“…Predicting students' performance in educational institutions is a major source of worry and interest for many researchers and governments around the world. It is important for educational institutions to monitor their students' performance and take appropriate action [1], [2]. University educators should evaluate the performance of their students to achieve desired goals and promote an environment of continuous improvement [3].…”