In the process of bankruptcy prediction models, a class imbalanced problem has occurred which limits the performance of the models. Most prior research addressed the problem by applying resampling methods such as the synthetic minority oversampling technique (SMOTE). However, resampling methods lead to other issues, e.g., increasing noisy data and training time during the process. To improve the bankruptcy prediction model, we propose cost-sensitive extreme gradient boosting (CS-XGB) to address the class imbalanced problem without requiring any resampling method. The proposed method’s effectiveness is evaluated on six real-world datasets, i.e., the LendingClub, and five Polish companies’ bankruptcy. This research compares the performance of CS-XGB with other ensemble methods, including SMOTE-XGB which applies SMOTE to the training set before the learning process. The experimental results show that i) based on LendingClub, the CS-XGB improves the performance of XGBoost and SMOTE-XGB by more than 50% and 33% on bankruptcy detection rate (BDR) and geometric mean (GM), respectively, and ii) the CS-XGB model outperforms random forest (RF), Bagging, AdaBoost, XGBoost, and SMOTE-XGB in terms of BDR, GM, and the area under a receiver operating characteristic curve (AUC) based on the five Polish datasets. Besides, the CS-XGB model achieves good overall prediction results.
1 January 2022 in Indonesian Journal of Electrical Engineering and Computer Science
This paper aims to analyze the learning behavior of Thai learners by using a computer-based learning system for English writing. Three main objectives were set: the development of a computer-based learning system, automatic behavior data collection, and learning behavior analytics. Firstly, the system is developed under a multidisciplinary idea that is designed to integrate two concepts between the self-regulated learning model and components of natural language processing. The integration design encourages self-learning in the digital learning environment and supports appropriate English writing by the provided component selection. Second, the system automatically collects the writing behavior of a group of Thai learners. The data collected are necessary input for the process of learning analytics. Third, the writing behaviors data were analyzed to find the learning behavioral patterns of the learners. For learning analytics, behavior sequential analysis was used to analyze the learning logs from the system. The 31 undergraduate students are participated to record writing behaviors via the system. The learning patterns in relation to grammatical skills were compared between three groups: basic, intermediate, and advanced levels. The learning behavior patterns of the three groups are different that use for reflecting learners and improving the learning materials or curriculum.
1 June 2025 in IAES International Journal of Artificial Intelligence (IJ-AI)
This research aims to improve the prediction’s model for survival time of lung cancer patients by using outlier detection, hyper-parameter optimization, and machine learning technique. The research compares the performance of several methods including multilayer perceptron (MLP), decision tree (DT), linear regression (LR), Bagging, XGBoost, and random forest (RF). The dataset used for the experiment is obtained from the surveillance, epidemiology, and end result (SEER) cancer database, which contains diagnoses data from 2004 to 2015. The total number of records used is 196,031 with 22 features. 10-fold cross-validation is used for training and testing sets. The evaluation metrics are root mean square error (RMSE), mean squared error (MSE), R-squared (R2), and mean absolute error (MAE). The results show that the lung cancer patient survival prediction model using the optimized XGBoost (O-XGBoost) model performs the best with an RMSE of 13.74 and outperforms the baseline-XGBoost model as well as other models. This research will be useful for developing a clinical decision support system for the care of lung cancer patients. Physicians can use the developed model to assess the patient’s chance of survival in order to plan more effective treatment.
The International Workshop on Artificial Intelligence for Signal, Image Processing, and Multimedia (AI-SIPM) aims to provide a platform for researchers, practitioners, and industry professionals to exchange ideas, discuss recent advancements, and explore future directions in the field of artificial intelligence (AI) applied to signal processing, image processing, and multimedia technologies. This workshop will feature presentations of novel research findings, practical applications, and innovative solutions addressing various challenges and opportunities in AI-driven signal and image processing, as well as multimedia analysis and understanding. Researchers and practitioners from academia, industry, and government agencies are invited to submit their original research contributions and participate in discussions that foster collaboration and knowledge sharing across different domains. Through this workshop, we aim to accelerate advancements in AI-driven technologies for signal processing, image analysis, and multimedia applications, contributing to the advancement of research and innovation in this rapidly evolving field.