Інструментарій інтелектуального аналізу даних для складних соціально-економічних процесів та систем

• Дата: 2022
• Автор: Obelets, Tetyana
• Формат: Стаття
• Мова: English
• Опубліковано: The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" 2022
• Теми: інтелектуальний аналіз даних; складні соціально-економічні системи; прогностичне моделювання; нейронні мережі; глибинне навчання; data mining; complex socio-economic systems; predictive modeling; neural networks; deep learning
• Онлайн доступ: http://journal.iasa.kpi.ua/article/view/256771
• Назва журналу: System research and information technologies

The paper considers discovering new and potentially useful information from large amounts of data that actualizes the role of developing data mining tools for complex socio-economic processes and systems based on the principles of the digital economy and their processing using network applications. The stages of data mining for complex socio-economic processes and systems were outlined. The algorithm of data mining was considered. It is determined that the previously used stages of data mining, which were limited to the model-building process, can be extended through the use of more powerful computer technology and the emergence of free access to large amounts of multidimensional data. The available stages of data mining for complex socio-economic processes and systems include the processes of facilitating data preparation, evaluation, and visualization of models, as well as in-depth learning. The data mining tools for complex socio-economic processes and systems in the context of technological progress and following the big data paradigm were identified. The data processing cycle has been investigated; this process consists of a series of steps starting with the input of raw data and ending with the output of useful information. The knowledge obtained at the data processing stage is the basis for creating models of complex socio-economic processes and systems. Two types of models (descriptive and predictive) that could be created in the data mining process were outlined. Algorithms for estimating and analyzing data for modeling complex socio-economic processes and systems in accordance with the pre-set task were determined. The efficiency of introducing neural networks and deep learning methods used in data mining was analyzed. It was determined that they would allow effective analysis and use of the existing large data sets for operational human resources management and strategic planning of complex socio-economic processes and systems.