In the modern world of the fintech industry, tax changes are one of the key problems, especially with fixed loans. This study examines the Tax Buffer mechanism, designed to effectively manage tax obligations that vary depending on the jurisdiction and stages of delivery of goods. The main task of the mechanism is to automatically recalculate taxes to minimize the risk of errors and reduce the burden on the accounting and legal departments of the company. The implementation of this solution allows you to reduce the number of manual operations, reduce transaction costs and improve the customer experience by eliminating the need to notify users of every change in the amount of taxes. The results of the implementation of the mechanism have shown its high efficiency: a significant reduction in the number of errors and financial disputes, as well as an increase in operational efficiency. The Tax Buffer mechanism is an important innovation that helps to increase the resilience of fintech companies to changes in tax legislation.

Zenodo DOI:-  https://doi.org/10.5281/zenodo.13895299

This study explores the application of machine learning algorithms for detecting anomalies in GitHub data to enhance the evaluation of technological projects. The research aims to develop a robust methodology for identifying data anomalies, such as artificial activity spikes, that can distort project assessments. Methods such as Isolation Forest, One-Class SVM, and advanced deep learning techniques like autoencoders and GANs are employed to analyze and identify irregular patterns in GitHub repositories. The findings demonstrate that these algorithms effectively detect both obvious and subtle anomalies, offering reliable insights into project authenticity. The proposed conceptual model integrates these methods into a scalable system, enhancing transparency and accuracy in technological project evaluation. The novelty of this work lies in its comprehensive approach to analyzing GitHub data, combining traditional and deep learning techniques to improve the reliability of assessments, making it a significant contribution to the field.

This paper discusses methods for preventing SQL (Structured Query Language) injections in identity and access control (IAM) systems. SQL injections represent one of the most serious threats to web security, allowing attackers to gain unauthorized access to and modify data. The main security methods include filtering input data, using prepared statements and parameterization, implementing stored procedures, restricting access rights, and regularly updating software. Effective privilege management and database activity monitoring also play a key role in preventing attacks. The introduction of these measures helps protect confidential information, ensures reliable authentication and authorization, and maintains data integrity. The paper highlights the importance of an integrated approach to database security in the face of growing cyber threats.

Zenodo DOI:- https://doi.org/10.5281/zenodo.13895346

Spike-wave discharges (SWD) are crucial biomarkers in the diagnosis and monitoring of neurological disorders such as epilepsy. Accurate classification of SWD is essential for effective clinical interventions and improving patient outcomes. This study presents a novel approach for classifying spike-wave discharges using the Short-Time Fourier Transform (STFT). By leveraging STFT's capability to analyze non-stationary signals, we extract time-frequency features from EEG recordings to accurately distinguish SWD from other brain activities. The extracted features are then classified using machine learning algorithms, providing high accuracy in identifying SWD events. Performance evaluation demonstrates that the proposed STFT-based method offers significant improvements in classification accuracy and computational efficiency compared to traditional time-domain analysis. The study's findings highlight the potential of STFT in real-time applications for automated seizure detection, contributing to advancements in neurological disorder diagnostics.

This paper examines the use of unsupervised machine learning and vector models in the design and optimization of retail channels for telecommunications services. Unsupervised machine learning allows you to analyze and identify hidden patterns in large volumes of untagged data, which is especially important in a dynamically changing consumer market. Vector models, in turn, provide high accuracy of demand forecasting and inventory management, contributing to an increase in the efficiency of trading channels. The synergy of these technologies allows companies to improve customer experience, optimize operational processes and increase competitiveness in the market. The main focus of the work is on data processing methods, including correlation analysis, the use of the support vector machine (SVM) method and its adaptation to solve problems related to predicting customer behavior and optimizing logistics processes.

Zenodo DOI:- https://doi.org/10.5281/zenodo.13895369