Authors

An approach to the design of a neural network for the formation of an individual trajectory of knowledge testing

The paper discusses the issues of implementing an adaptive testing system based on the use of artificial neural network (INS) modules, which should solve the problem of intelligent choice of the next question, forming an individual testing trajectory. The aim of the work is to increase the accuracy of the INS to form the level of complexity of the next test question for two types of architectures – direct propagation (FNN – Feedforward Neural Network) and recurrent with long-term short-term memory (LSTM – Long-Short Term Memory). The data affecting the quality of training are analyzed, the architectures of the input layer of the direct propagation INS are considered, which have significantly improved the quality of neural networks. To solve the problem of choosing the thematic block of the question, a hybrid module structure is proposed, including the INS itself and a software module for algorithmic processing of the results obtained from the INS. A study of the feasibility of using direct propagation ANNs in comparison with the LSTM architecture was carried out, the input parameters of the network were identified, various architectures and parameters of the ANN training were compared (algorithms for updating weights, loss functions, the number of training epochs, packet sizes). The substantiation of the choice of a direct distribution network in the structure of the hybrid module for selecting a thematic block is given. The above results were obtained using the Keras high-level library, which allows you to quickly start at the initial stages of research and get the first results. Traditionally, learning has taken place over a large number of eras. Read more...

Assessment of the bank’s operational risk criticality level based on neural network technologies

The article is devoted to the issues of controlling the operational risks of a credit institution arising in the process of using IT technologies. Among banking risks, operational risk occupies a special place, primarily due to the fact, that it affects various areas of banking activity and is difficult to separate from other types of risk. Operational risks arise, among other things, as a result of downtime or incorrect operation of technical systems and equipment. Due to the constant growth in the degree of automation of banking business processes, new IT risk groups are emerging that can have a significant impact on the activities of a credit institution. The aim of the work is to create an artificial neural network using the high-level Keras library in Python, which automatically controls the level of criticality of the IT risk that has arisen. In the article, based on the analysis of risk events associated with the use of IT technologies, the data flows entering the input of the neural network is identified and its structure is determined. The paper also presents the results of training a neural network created by the authors based on the generated data sets. The use of intelligent methods for assessing the level of criticality of operational IT risk allows you to quickly take measures to minimize the consequences, and thus reduce direct and indirect losses. In connection with the above, the automation of operational risk management based on the use of neural network technologies is currently one of the most urgent tasks for credit institutions. The results obtained are new and can be used by credit institutions in the process of building automated systems for monitoring and managing operational risks. Read more...