Cybernetic cognitive model for describing the financial health of it gaming company ⋆ Olena Kryvoruchko1,†, Alona Desiatko1,*,†, Ihor Karpunin1,†, Svitlana Symonenko2,† and Olena Furman3,† 1 State University of Trade and Economics, 19A Kyoto str., 02156 Kyiv, Ukraine 2 Dmytro Motornyi Tavria State Agrotechnoligical University, 66 Zhukovskyi str., 69063 Zaporizhzhia, Ukraine 3 Kremenets Regional Humanitarian and Pedagogical Academy named after Taras Shevchenko, 1 Litseyna str., 47003 Kremenets, Ukraine Abstract A software implementation of a cognitive model in Python using the popular NetworkX and Matplotlib libraries is proposed. This software implementation allows visualizing the influence graphs of different concepts, as well as building histograms showing the strength and direction of these influences. Thus, the software provides a convenient and visual tool for analysts and managers of the company, allowing them to promptly assess the financial condition of the company and forecast its future changes based on iterative data analysis and model updates. The analysis of the obtained histograms shows the distribution of the strength of influence of different concepts in the model. These histograms demonstrate both positive and negative relationships between concepts, as well as the frequency of their manifestation within the developed model. It was found that the use of cognitive modeling taking into account weakly structured concepts contributes to a deeper understanding of economic processes related to the financial condition of the company. This approach makes it possible to identify hidden relationships and trends that can have a significant impact on the financial performance of the company in the long term. Keywords cognitive model, cybernetic modeling, concept, algorithmic language, Python 1 1. Introduction in financial management, which helps to improve financial planning, optimize costs, and improve the overall Analysis of the financial condition (FC) of business entities performance of BE. In most countries, companies are (hereinafter referred to as BE, i.e. enterprises, companies, required to provide regular financial statements by organizations, etc.) plays a key role in the modern business established standards, and analyzing FC and FPI helps and economy of Ukraine. The management of a BE needs to businesses not only to comply with these requirements but have an accurate understanding of its FC to make informed also to identify possible areas for improvement in internal strategic decisions, which may relate to investment projects, control and auditing. business expansion, changes in operations, and other Early diagnosis of financial problems, including important aspects of management. leveraging the potential of cyber modeling, and timely Understanding a BE’s current FC will allow remedial action can prevent bankruptcy and minimize the management to assess its resilience to various economic negative impact on BE. Comprehensive analyses of BE’s FC shocks, such as economic crises, changes in market and FPI will allow the timely identification of signs of conditions, or internal problems, which is particularly financial instability and the taking of necessary actions. important for identifying potential risks and developing IT gaming companies operate in a rapidly changing mitigating measures. Investors, creditors, suppliers, and environment where innovation and user experience play a other stakeholders rely on financial reports and analyses to key role and this creates an excellent environment for the assess the creditworthiness and reliability of an enterprise application of cognitive modeling, as many interrelated by monitoring its financial performance indicators (FPI) and factors need to be considered. In the gaming industry, there other markers. are different revenue sources such as game sales, in-game Accurate and reliable FPIs, as well as other data, are purchases, advertising revenue, and others, which will necessary to attract investment, obtain credit from banks, allow us to build a multidimensional model with a variety and establish long-term partnerships. Analysis of the FC of concepts and make our analysis more comprehensive and and FPI of BE allows to identify of weaknesses and strengths interesting. Note that it is important for a game company to CPITS-II 2024: Workshop on Cybersecurity Providing in Information 0000-0002-7661-9227 (O. Kryvoruchko); and Telecommunication Systems II, October 26, 2024, Kyiv, Ukraine 0000-0002-2284-3418 (A. Desiatko); ∗ Corresponding author. 0000-0002-6442-3446 (I. Karpunin); † These authors contributed equally. 0000-0003-0599-3999 (S. Symonenko); olena_909@ukr.net (O. Kryvoruchko); 0000-0002-3175-1814 (O. Furman) desyatko@gmail.com (A. Desiatko); © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). i.karpunin@knute.edu.ua (I. Karpunin); svitlana.symonenko@tsatu.edu.ua (S. Symonenko); ramskaoa@meta.ua (O. Furman) CEUR Workshop ceur-ws.org ISSN 1613-0073 276 Proceedings consider not only financial metrics, but also factors such as dynamic models that take into account time delays and non- player engagement, customer satisfaction, and development linear effects in the system. speed. These metrics directly affect the financial health of the 3. The purpose of the paper company and need to be analyzed carefully. It is important to note that the gaming industry is at the forefront of The purpose of the paper is to develop a cybernetic model technological innovation, making it ideal for testing and of cognitive modeling for the analysis of the financial implementing advanced data analytics and cognitive condition and BE indicators for more accurate prediction modeling techniques, and in turn, this will allow us to and assessment of the impact of various factors on financial demonstrate the potential of our methods in environments results in the example of an IT gaming company. where a high degree of adaptability and predictive power is required. 4. Methods and models Additionally, we note that the gaming industry is highly Consider implementing the cognitive model in the form of competitive, making it important to analyze the impact of a directed graph in Python, which allows us to visualize the the competitive environment on a company’s financial relationships between financial indicators and conduct health. This reinforces the need to use cognitive modeling simulation modeling to predict various scenarios. This for a more accurate and informative analysis. IT gaming approach will potentially help management to make companies have a lot of data about users, their behavior, informed management decisions and improve the financial sales, and marketing campaigns, therefore, this will provide health of the company. A cognitive model is a network of excellent opportunities for data collection and analysis, as concepts and links between them that reflect cause-effect well as for building models based on this data. relationships and interrelationships. To realize such a model In the gaming industry, constant development and in the form of a graph would require: changing conditions require the use of complex models to analyze and forecast the financial health of a company. The  Nodes—represent concepts or variables such as diverse revenue sources in the gaming industry allow for a financial performance indicators, external factors, etc. more multi-dimensional and comprehensive model, which  Edges—directed links between nodes that show the helps to more accurately assess a company’s financial influence of one concept on another. condition (FC). Factors affecting customer satisfaction and engagement This approach will allow: have a direct impact on the revenue and overall financial stability of a company, making them important to analyze.  Visualize and analyze the relationships between The gaming industry is at the forefront of using new various financial indicators and external factors. technologies, making it ideal for testing and implementing  Use graph theory methods to analyze the structure new methods of data analysis. and behavior of a model. 2. Analysis of recent studies and Also with this kind of cybernetic modeling, it is quite easy to modify and extend the model by adding new nodes publications and links. As was shown [1–6] cognitive models allow for visualizing At the final stages of the research and to adapt the and analyzing complex relationships between different proposed model to a specific object (IT gaming company) variables and indicators, which is especially relevant for the we will need to: identify company-specific FPIs, external tasks of assessing the company’s FC. The use of cybernetic factors, and other parameters; update the nodes and links in modeling and object-oriented programming (hereinafter the cognitive map by the peculiarities of the IT gaming OOP) provides additional advantages for the construction company; test and validate the model on the company’s and application of such models [4]. historical data. Cybernetics, as the science of control and The development of a software product architecture communication in complex systems, offers a methodology (hereinafter referred to as PA) for cognitive modeling of the for the analysis and modeling of systems with feedback. In FC and evaluation of its FPI requires a thorough analysis of the context of financial analysis, cybernetic modeling helps various aspects, including the choice of programming to solve a wide range of theoretical and applied problems, language. Below we present a brief analysis of the which are already reworked [7–18]. architecture and justification of the potential of using In particular, in financial systems, many variables are different programming languages for this task, see Fig. 1. interrelated through feedback loops (e.g., investments affect The analysis of the software product architecture is shown profits, which in turn affect future investments). Cybernetic conceptually in Fig. 1. A brief description is given below. modeling can accurately account for such relationships. In addition, financial indicators and company conditions change 1. Cognitive modeling module: graph visualization over time, which is especially relevant at the present moment, (creating and displaying a cognitive map); analysis when Russia’s aggression against Ukraine continues unabated and simulation (algorithms for analysis and and the financial condition of many companies has deteriorated simulation based on the cognitive model). for objective reasons. Cybernetic modeling will allow building 2. Data module: data collection (integration with external data sources (financial reports, and 277 market data); data warehouse (database for storing manage their operations. Consequently, at the historical data and modeling results). implementation stage of a particular system, it will be 3. Data processing module: data cleaning and necessary to adapt the architecture to interact with specific preprocessing (preparing data for analysis); data ERP systems such as SAP, Oracle, and Microsoft Dynamics. analysis (applying machine learning (ML) and In addition, it is important to consider the specifics of data statistical techniques to analyze financial sources, which will require customizing the architecture to performance). handle different types of data (structured, unstructured, 4. Reporting and visualization module: report semi-structured data) and volumes. Such aspects of generation (creating reports based on modeling development as scalability and performance of such a results); data visualization (interfaces for system are also extremely important, as different companies interactive visualization of data and analysis may have different requirements for the scalability and results). performance of the system for FC monitoring and FPI 5. User interface (UI): web interface (access to the modeling. system functionality via web browser); mobile For example, small businesses can do this with minimal application (access to the system functionality via computing power and simple analytical tools. Large mobile devices). businesses may already require high-performance and scalable solutions for processing large amounts of data and The proposed architecture, see Fig. 1, is a flexible complex analytical tasks. Also important is such an aspect framework that can be enhanced and adapted to a of the problem as data security and confidentiality, which is company’s specific requirements and business processes. especially relevant in the conditions of martial law and Different companies may operate in different industries, military aggression unleashed by the Russian Federation each with its unique characteristics and requirements. against Ukraine. Different companies in such a situation For example, an IT Gaming Company may require more may have different requirements for data security and flexible and faster data analysis to assess financial health in confidentiality. For example, financial companies may a dynamically changing market environment. A require more stringent security measures and compliance manufacturing company may require more detailed cost with regulatory standards (e.g. GDPR, PCI DSS) at the stage analysis and supply chain management, as well as of development and implementation of such a PA. At the consideration of long production cycles, while a financial same time, technology companies may focus in parallel on institution needs more regulatory compliance and financial protecting intellectual property and customer data in terms risk analysis. of reference. In addition to the above, note that different companies may use different data sources and proprietary systems to Data Module Cognitive Modeling Module Tasks: Tasks: 1. Data collection (integration with external data sources like 1. Visualization of the graph (creation and financial reports, market data); display of a cognitive map); 2. Data storage (database for storing historical data and 2. Analysis and modeling (algorithms for analysis and simulation modeling based on a modeling results). cognitive model). Data Processing Module Tasks: 1. Data cleaning and preprocessing Database (preparation of data for analysis); 2. Data analysis (applying machine learning (ML) methods and statistical methods for analyzing FPI . Reporting and Visualization Module Tasks: 1. Report generation (creating reports based on modeling results); 2. Data visualization (interfaces for interactive visualization of data and analysis results). User Interface (UI) Tasks: 1. Web interface (access to system functionality through a web browser); 2. Mobile application (access to system functionality through mobile devices). Figure 1: Conceptual scheme of the developed PA The specifics of business processes will a priori affect the companies with unique workflows and user experience module that implements the user interface. For example, an needs, such as game designers or core developers of such intuitive interface for employees may be a primary software. requirement for companies with non-technically savvy The general architecture, shown in the form of modules users, while a customizable interface may be a priority for in Fig. 1, allows only laying down the basic principles and 278 approaches to the creation of such a system, which can be technologies and modern programming methods opens new adapted to the specific needs of the company. This ensures opportunities for the analysis and forecasting of FC, flexibility, modularity, reusability, etc. improvement of management processes, and creation of Although this is beyond the scope of the tasks to be intelligent information systems. These aspects not only solved in this paper, we will nevertheless note some possible contribute to scientific progress but also offer practical improvements to such a system. Firstly, these are possible solutions for businesses that can significantly improve their additional modules, the introduction of which is efficiency and sustainability. conditioned by the specific tasks of the company. For The first step is to build a cognitive model that will example, these may be modules related to risk management represent the main FPIs and their relationships (let us or supply chain analysis. Secondly, the improvements may illustrate this with a simple example). For this purpose, we concern the task of integration with new data sources, since use an oriented graph, where the vertices (nodes) will setting up integration with new management systems and represent concepts such as revenues, expenses, profits, data sources used in the company is important for the assets, and liabilities, and the edges will represent the links subsequent correct modeling of the FPI and assessment of between these concepts, see Fig. 2. the company’s FC as a whole. Thirdly, it may be necessary The code illustrating the creation of such a graph is to optimize performance and tune the system to cope with shown below. high load levels and large data volumes. Finally, possible improvements may concern the security settings of such a #Import the required libraries PA, i.e. implementation of additional security measures and import networkx as nx import matplotlib.pyplot as plt verification of compliance with regulatory requirements for information security. #Create an empty oriented graph After building the cognitive model, the next step is to G=nx.DiGraph() develop a simulation model that will allow us to analyze #Add nodes (financial concepts) various scenarios of changes in the financial condition of nodes=[“Income”, “Costs”, “Profit”, “Assets”, the company. For this purpose, we will use data analysis and “Obligations”] machine learning methods available in Python. G.add_nodes_from(nodes) Cognitive technologies such as cognitive maps and cognitive modeling provide a new way to represent and #Add edges (links between concepts) edges=[(“Income”, “Profit”), (“Costs”, “Profit”), analyze complex systems. As shown in [2–4], traditional (“Profit”, “Assets”), (“Assets”, “Obligations”)] financial analysis techniques are often limited in their G.add_edges_from(edges) ability to handle loosely structured problems. Cognitive modeling based on cybernetic tools will allow us to account #Visualise the graph plt.figure(figsize=(10, 7)) for fuzzy and uncertain relationships between financial pos=nx.spring_layout(G) ratios. For example, cognitive maps will allow visualization nx.draw(G, pos, with_labels=True, and deeper analysis of causal relationships between node_colour=“lightblue”, node_size=3000, font_size=12, different financial metrics, which will improve the font_weight=“bold”, arrows=True) plt.title(“Cognitive model of financial status”) understanding of financial health dynamics. OOP and plt.show() modern Python libraries (e.g. NetworkX for graphs and Scikit-learn for machine learning) provide powerful tools for implementing cognitive models. Thus the OOP methodology allows cognitive models to be structured as classes and objects, which simplifies their development, testing, and modification. Modern Python libraries, which we will use during the implementation of our project, will allow us to automate the process of data analysis and forecasting, making cognitive models more efficient and accurate. Summarising all of the above, it is not difficult to see that the development and implementation of cognitive models for BE FC assessment contributes to both the theoretical and practical part of computer science, as it extends the existing theories and methods of cognitive modeling, the scope of their application to new areas, such as financial analysis, and the development of new algorithms, among others. The creation of new tools and systems for business, which can improve management and decision-making processes, will be able to improve the financial stability and competitiveness of enterprises, given Figure 2: A cognitive model that will represent the main the situation in which the Ukrainian economy is at war with FPIs and their relationships in the form of a directed graph RF. Thus, the connection between cognitive modeling and (implementation in PyCharm) BE FC evaluation is a new and promising approach in computer science, and the integration of cognitive For a complete code, in order to account for the changing influence of concepts on each other, we will use influence 279 matrices for the illustration below. These matrices will In histogram 4(a), it can be seen that most of the weight contain weighting coefficients that actually determine the values are between 0 and 0.4, and some negative weights are strength of the connection between concepts. The also present, indicating a negative impact. matplotlib library can be used to visualise the change in the The histograms, see Fig. 4 a), b) c) show the distributions degree of influence. of the weights of the links between concepts in the cognitive The above small example illustrates how changing the model. weighting of concept influence affects the structure of the cognitive model, and visualizes this using histograms. a) b) Figure 3: Examples of a) and b) structures of a cognitive model that takes into account the influence of concepts on each other in the format of different values of weights (implementation in PyCharm) Fig. 4 b) shows the Strong Influence Strength Histogram. The concept affects Customer Satisfaction with a weight Histogram in Fig. 4 c) shows a narrower distribution of of 0.4. values, indicating that all relationships between concepts The concept affects Employee Performance with a are weakened. weight of 0.1. Let’s consider the meaning of concepts in more detail. Positive Weights indicate the positive impact of one The concept Revenue affects Market Share with a concept on another. For example, an increase in Market weight of 0.2 and also affects Costs with a weight of -0.4. Share has a positive impact on Revenue. The concept Costs affects Customer Satisfaction with a Negative Weights indicate a negative impact, e.g. an weight of -0.2. increase in Costs harms Customer Satisfaction. The Market Share concept affects Revenue with a weight of 0.3. a) b) c) Figure 4: Distribution of weights of links between concepts in the cognitive model Changes in concept weights can be easily traced by concepts change when the influence is strengthened or comparing histograms, while graphs and visualization of weakened. This will help system analysts and researchers the concept network help to understand the structure and understand which concepts have the greatest influence on a intensity of influence between concepts. Thus, even with cognitive model and how changes in one part of the system such simple examples implemented in the PyCharm can affect other parts. environment, we can conclude that the use of histograms In our view, the implementation of a cognitive model to allows us to visualize how the weights of links between assess an enterprise’s FC in the form of a decision support 280 system (DSS) or an intelligent system (IS) offers many [3] O. Chukurna, et al., Formation of Methodical advantages. Cognitive models can predict future PEs based Foundations for Assessing the Innovative on current data and historical trends, which in turn will Development Potential of an Industrial Enterprise, allow companies to make more informed decisions and Naukovyi Visnyk Natsionalnoho Hirnychoho develop risk management strategies. In addition, the Universytetu, 4 (2020) 146–151. integration of a cognitive model into an IPS will allow real- [4] O. Sosnovska, M. Zhytar, Financial Architecture as time monitoring of an enterprise’s FPs, identifying the Base of the Financial Safety of the Enterprise, deviations and potential threats, and taking timely Baltic J. Econom. Stud., 4(4) (2018) 334–340. corrective action. Cognitive models must be able to take into [5] V. Tkachenko, et al., Development and Effectiveness account many factors affecting the financial state of the of Financial Potential Management of Enterprises in enterprise, which is especially important for complex and Modern Conditions, Financial and Credit Activity multi-component business processes of IT gaming Problems of Theory and Practice, 3(30) (2019) 85–94. companies. The developed SPPR with a cognitive model [6] Y. Y. Varlanov, O. Y. Varlanov, Modeling the Financial should be interactive, allowing users to modify input data Condition of Enterprises: An Essential Approach to and observe the results, which will help in analyzing “what- Integrated Assessment, J. Econom. Sci. (59) (2012) if” scenarios. Such a system will also be able to adapt to 139–146. changes in the external and internal environment of the [7] N. Mazur, et al., Improvement of Controlling in the enterprise. Note that automating FC analysis and Financial Management of Enterprises, TEM J. 10(4) forecasting will reduce the likelihood of human error and (2021). subjectivity in decision-making. [8] L. Ogiela, M. R. Ogiela, Cognitive Systems for The above methodology allows repeating experiments Intelligent Business Information Management in with changing initial conditions and model parameters, Cognitive Economy, Int. J. Inf. Manag. 34(6) (2014) which provides flexibility and adaptability to the analysis. 751–760. This is especially important for assessing the impact of new [9] L. Ogiela, Towards Cognitive Economy, Soft Comput. concepts and changes in the company’s business processes. 18 (2014) 1675–1683 (2014). doi: 10.1007/s00500-014- 1230-z. 5. Conclusions [10] H. O. Aifuwa, M. Saidu, Board Cognitive Diversity and Firm Performance Nexus: Evidence from Nigeria, The main findings of the research were as follows and the Int. J. Manag. Innov. Entrepreneurial Res. 6(2) (2020) following conclusions were drawn. 88–99. [11] B. Zyznarska-Dworczak, Sustainability Accounting— 1. We developed a software implementation of the Cognitive and Conceptual Approach, Sustainability, cognitive model in Python using NetworkX and 12(23) (2020) 9936. Matplotlib libraries. This software implementation [12] M. Petrova, I. Buzko, Y. Dyachenko, Cognitive, allows visualizing graphs and histograms of Intelligence Technologies and Economic Foundations concept influences, as well as iterative data of Teaching of International Economic Relations and analysis and model updating. The software Tourism, Engineering for Rural Development, 17 provides a convenient and visual tool for analysts (2018) 1102–1106. and managers of the company, allowing them to [13] N. Morozko, V. Didenko, Financial Management of promptly assess the financial condition and Small Organizations based on a Cognitive Approach forecast future changes. (2018). 2. Histograms showing the distribution of the [14] H. Wang, et al., The Effect of Digital Transformation strength of influence of different concepts in the Strategy on Performance: The Moderating Role of model were obtained. The histograms show both Cognitive Conflict, Int. J. Conflict Manag. 31(3) (2020) positive and negative relationships, as well as the 441–462. frequency of their manifestation in the model. [15] R. K. Reger, A. S. Huff, Strategic Groups: A Cognitive 3. It is shown that the use of cognitive modeling Perspective, Strategic Manag. J. 14(2) (1993) 103–123. taking into account weakly structured concepts [16] O. Kryvoruchko, et al., Cognitive Modeling and contributes to a better understanding of economic Formation of the Knowledge Base of the Information processes related to the financial condition of the System for Assessing the Rating of Enterprises, Int. J. company and allows to identify of hidden Electron. Telecommun. (2023) 697–705. relationships and trends. [17] M. Chyzhevska, et al., Dual Impact of Crypto Industry Technologies on the Energy Poverty, in: n References Cybersecurity Providing in Information and [1] L. Guryanova, T. Klebanova, T. Trunova, Modeling Telecommunication Systems, vol. 3421 (2023) 293– the Financial Strategy of the Enterprise in an Unstable 299. Environment, Economic Studies, 26(3) (2017). [18] V. Lakhno, et al., Allocation of Organizational and [2] L. M. Malyarets, et al., The Modeling of Multi-Criteria Financial Resources of the Information Protection Assessment Activity in Enterprise Management Side using a Genetic Algorithm, Informatics and (2019). Cybernetics in Intelligent Systems, CSOC 2021, LNNS, 228 (2021). doi: 10.1007/978-3-030-77448-6_5. 281