Scientific works of the Donetsk National Technical University. Series: "Computerengineering and automation"

BUSINESS MODELS IN STARTUP GROWTH FORECASTING

Yakiv (Jacob) Baytelman — Thu, 28 Mar 2024 00:00:00 +0200

A start-up is the IT industry specific form of commercial enterprise with its own peculiarities not observed in other forms of business ventures. Hands-on purposes require a toolset for start-up growth modelling and forecasting as well as for their evaluation; business models belong to such tools. Advantages of business modelling is not always obvious to start-up founders, up to the moment when it becomes a part of requirements from investors. A form that allows quick modelling greatly simplifies evaluation and triage of start-ups by investors and thus can become one of formatting factors for regional or national start-up ecosystems in Ukraine. Based on the recent publications this research offers an example of a business model and suggests several key aspects for more practical application of business modelling for the sake of start-up growth forecasting, including expression of main milestones in the financial projection.

REQUIREMENT PRIORITIZATION IN THE DEVELOPMENT OF SOFTWARE PROJECTS FOR CRITICAL INFRASTRUCTURE OBJECTS

IAROSLAV DOROHYI, Olena Doroha-Ivaniuk — Thu, 28 Mar 2024 00:00:00 +0200

The objective of the study is to develop an algorithm for prioritizing requirements in the development of software for critical infrastructure object projects. Requirement development is a fundamental phase in any software project, as this phase involves the identification, processing, and manipulation of requirements. The primary source of these requirements is project stakeholders, taking into account project constraints and limits. The number of requirements varies for each software project for a critical infrastructure object, hence the term requirement prioritization pertains to determining the priority order of executing software requirements based on considerations and decisions of stakeholders.

Various proposed optimization algorithms are employed to address optimization tasks. This paper presents the main stages of basic optimization algorithms, some of their modifications aimed at enhancing their efficiency in solving such types of problems. Additionally, a hybrid approach based on WOA and GWO optimization algorithms is proposed, combining the advantages of each algorithm to determine the priority of requirements for critical infrastructure object software. Furthermore, a dataset from the SKUDA project is provided, utilized in this research, meeting the requirements of a real software project for evaluating the proposed method.

The scientific novelty lies in the modification, application, and combination of results from well-known GWO and WOA algorithms to address the requirement prioritization task for critical infrastructure object software projects. The proposed algorithm achieves an accuracy of 92% for the proposed set of requirements.

USE OF MACHINE LEARNING TOOLS AND PYTHON LIBRARIES FOR PREDICTION THROUGH REGRESSIONS

Hanna Telychko, Yakiv (Jacob) Baytelman, Daria Zhukovska — Thu, 28 Mar 2024 00:00:00 +0200

The purpose of this work is forecasting the average check amount depending on the time spent by customers in the retail area and forecasting the average check amount based on seasonal demand characteristics considering the constant annual price growth.

Forecast methods were analysed. The use of Python libraries was considered. The code was developed for solving the above-mentioned forecasting tasks through linear, polynomial and random forest regressions, specifically, the search for the dependence of the average check amount on the time spent by customers in the retail area and the dependence of the average check amount on seasonal price fluctuations over several years. A comparison of the results of linear and polynomial regression was made under conditions of smaller or larger volumes of the input data, explanations were provided regarding the appropriateness of choosing one or the other when modelling non-cyclical processes and why the random forest model provides adequate results for cyclical processes. The source code and examples of input data were shared for public access.

Scientific novelty lies in the ways of applying regressions for modelling and forecasting the average check amount depending on the time customers spend in the retail area as well as the average check amount depending on seasonal demand characteristics with consideration of constant price growth.

The selected examples of cyclical and non-cyclical economic phenomena are the most common ones, and practitioners face similar tasks daily. Therefore, the results of this work provide them with ready-made solutions that require minimal adaptation to practical needs. Additionally, it demonstrates the feasibility of deploying them in the AWS cloud environment and the potential for integration with various data sources and other information systems.

CONCEPTUAL FOUNDATIONS OF GLOBAL RESILIENCE OF A SMART STATE

IAROSLAV DOROHYI, Iryna Berdychenko — Thu, 28 Mar 2024 00:00:00 +0200

This article is dedicated to the examination of the conceptual foundations of the global resilience of a smart state. The authors explore the contemporary dimension of Ukraine's development in the context of the integration of technologies and innovations into all aspects of life. In particular, the article investigates the impact of information technologies, artificial intelligence, and other modern technologies on the efficiency of governance, socio-economic development, and ecological resilience.

The article provides a detailed analysis of key aspects of the creation and functioning of smart states, including the role of digital infrastructures, open data, and e-government. The authors analyze the principles of interaction between a smart state and citizens, businesses, and other members of society to achieve a high level of resilience and development.

The article also examines challenges and risks associated with the implementation of modern technologies in the state system and proposes strategies for ensuring cybersecurity and privacy protection in the digital environment. Special attention is given to the ideas of resilience development and ethical aspects of technology use to achieve global resilience of a smart state, understanding such definitions as digital resilience and global resilience, and accordingly, determining their structure and patterns of use.

SECURITY AND PROTECTION OF EDUCATIONAL LMC SYSTEMS

Olena Liubymenko, Nataliia Maslova — Thu, 28 Mar 2024 00:00:00 +0200

Information technologies play a significant role in the educational process and ensuring quality learning outcomes in the context of distance education. A modern trend is the development of interactive systems, which include elements of audio and video materials, graphics, presentations, internet links, materials from various sources, and in different formats. The addition of interactive content to educational systems increases the risks of information security in modern LMC systems. Emphasis is placed on the need to ensure the protection of software in systems, educational content hosted within them, learning outcomes, and participants' personal data. When building protection, attention should be paid to potential threats such as unauthorized access, flawed software, poor plugin updates, material copying, fraud, and cyber-attacks. Vulnerabilities of the most widespread modern LMC systems are analyzed. Attention is given to the possibilities of using cloud technologies to host system modules, educational materials, or learning outcomes on cloud services. Cloud application guarantees constant access to the learning system, reliable storage of materials, additional protection of confidential and personal information. Therefore, to ensure effective and safe learning considering modern interactive approaches to presenting educational materials, it is important to develop systems and implement technologies that provide constant access to educational content, reliable data protection (including personal data), information integrity, and compliance with confidentiality principles.