Spam represents a genuine irritation for email users, since it often disturbs them during their work or free time. Machine learning approaches are commonly utilized as the engine of spam detection solutions, as they are efficient and usually exhibit a high degree of classification accuracy. Nevertheless, it sometimes happens that good messages are labeled as spam and, more often, some spam emails enter into the inbox as good ones. This manuscript proposes a novel email spam detection approach by combining machine learning models with an enhanced sine cosine swarm intelligence algorithm to counter the deficiencies of the existing techniques. The introduced novel sine cosine was adopted for training logistic regression and for tuning XGBoost models as part of the hybrid machine learning-metaheuristics framework. The developed framework has been validated on two public high-dimensional spam benchmark datasets (CSDMC2010 and TurkishEmail), and the extensive experiments conducted have shown that the model successfully deals with high-degree data. The comparative analysis with other cutting-edge spam detection models, also based on metaheuristics, has shown that the proposed hybrid method obtains superior performance in terms of accuracy, precision, recall, f1 score, and other relevant classification metrics. Additionally, the empirically established superiority of the proposed method is validated using rigid statistical tests.

The recent pandemic had a major impact on online transactions. With this trend, credit card fraud increased. For the solution to this problem the authors explore existing solutions and propose an optimized solution. The solution is based on an extreme gradient boosting algorithm (XGBoost) and a teaching-learning-based-optimization algorithm. The dataset optimizes the hyperparameters of the XGBoost which is utilized as the main driver for the solution. The evaluation was performed among other similar techniques that have solved this problem successfully in the past. Standard performance metrics were applied which are accuracy, recall, precision, Matthews correlation coefficient, and area under the curve. The result of this research presents a dominant solution that was proposed and successfully outperformed all other compared solutions overall.

Numerous methods exist aimed at examining patterns in structured and unstructured financial data. Applications of these methods include fraud detection, risk management, credit allocation, assessment of the risk of default, customer analytics, trading prediction, and many others, creating a broad field of research named Financial data science. A problem within the field that remains significantly under-researched, yet very important, is that of differentiating between the three major types of business activities—merchandising, manufacturing, and service based on the structured data available in financial reports. It can be argued that, due to the inherent idiosyncrasies of the three types of business activities, methods for assessment of the risk of default, methods for credit allocation, and methods for fraud detection would all see an improved performance if reliable information on the percentage of entities’ business activities allocated to the three major activities would be available. To this end, in this paper, we propose a clustering procedure that relies on Principal Component Analysis (PCA) for dimensionality reduction and feature selection. The procedure is presented using a large empirical data set comprising complete financial reports for various business entities operating in the Republic in Serbia, that pertain to the reporting period 2019.

Artificial intelligence and internet of things (IoT) fields have contributed to the flourishment of the industry 4.0 concept. The main benefits include the improvements in terms of device communication, productivity, and efficiency. Nevertheless, there is a downside concerning the security of these systems. The amount of devices and their diversity prove a security risk. Due to this intrusion detection systems are paramount. This paper proposes a novel framework exploiting extreme gradient boosting machine learning model which is optimized by a modified version of the multi-verse optimizer metaheuristic. The UNSW-NB intrusion dataset was used for experimental purposes on which the other cutting-edge techniques were tested and compared. The results provide the proof of improvement as the proposed method outperformed all other overall metaheuristic performances. Furthermore, the units for truthfulness and polarity for the case have been established as a standard evaluation system. True and false positives exist alongside the same negative counterparts. The results provided by these metrics have been visualized and used for further comparison proving the superiority of the performance of the proposed solution.