How deep is your model? Network topology selection from a model validation perspective

Deep learning is a powerful tool, which is becoming increasingly popular in financial modeling. However, model validation requirements such as SR 11-7 pose a significant obstacle to the deployment of neural networks in a bank’s production system. Their typically high number of (hyper-)parameters poses a particular challenge to model selection, benchmarking and documentation. We present a simple grid based method together with an open source implementation and show how this pragmatically satisfies model validation requirements. We illustrate the method by learning the option pricing formula in the Black–Scholes and the Heston model.

FINANCIAL MODELING: PROBABILITY THEORETIC APPROACHES

Background. A large number of significant socio-economic events occur under the influence of unique factors. Formal application of probabilistic and statistical methods in such cases leads to analytical conclusions without sufficient scientific justification. Financial modeling reflects modern approaches to the probability interpretation, provides introduction and systematization of risk indicators, and the necessity of improving theoretical and probabilistic disciplines of economic orientation. Analysis of recent research and publications has shown that despite significant investigations, financial modeling is not theoretically complete scientific direction in terms of economic risk indicators and derivative characteristics, important scientific and practical problems remain unresolved in the analysis of socio-economic phenomena in unce­rtainty and implementation of modern achievements of scientists to the process. The aim of the article is to study theoretical and probabilistic concepts of socio-economic processes in conditions of uncertainty and uniqueness based on the financial modeling methods. Materials and methods. Analytical and statistical methods, methods of mathematical statistics and probability theory are used in the research process. Information database is data from trading sessions of world stock markets. Results. Theoretical and probabilistic concepts, including interpretations of probability and risk are considered through formalization of the analysis process by the subject of the socio-economic phenomenon in conditions of uncertainty. Models of typical stationary, dynamic, parity and dominant lotteries with introduced risk indicators are built. Risk is interpreted as the ratio of negative and favorable factors of the phenomenon information background. Relevant indicators are illustrated and calculated using various socio-economic and financial cases. Subjective-probabilistic modeling (SPM) in relation to decision-making in the financial market is studied as the development of Bayesian subjectivism. It has been shown that group consensus SPM-assessments of risk generate specific derivative financial instruments such as binary options, index derivatives, crypto-assets, etc. Conclusion. The results of the study showed the application effectiveness of financial modeling methods of risks assessment in financial markets, the prospects of relevant development in the field of financial engineering. Teaching economic disciplines, which are based on theoretical and probabilistic postulates, statistical and analytical-statistical procedures for calculating probabilistic indicators (probability, risk, prevention regulations, etc.), requires significant addition using the introduction of new methods of information analysis of social background, financial sphere to determine the optimal direction of development and investment activities. Keywords: risk ratio, probability interpretation, binary options, financial modeling, high-risk financial markets, subjective-probabilistic modeling.

Modeling the aggregate risk of common stockholder through the determined financial model

Subject. The article focuses on methods for modeling and quantifying the risk associated with common stockholders. Objectives. We perform a critical analysis and study how the existing risk assessment methods can be modified. The article demonstrates strengths and advantages of the determined financial model. Methods. The study is based on methods of the discourse analysis, mathematical statistics, financial modeling. Results. If the entity receives payments out of net profit, we show the modified formula for assessing the aggregate leverage and suggest using the term financial leverage in Russian. The chi-squared comparison method reveals the need to respect aggregate leverage restrictions. We also present formulae for assessing its minimum and maximum. In this study, we provide a broader view of the financial mentality as a concept, quantify to what extent the decision-maker is prone to risk. Conclusions and Relevance. The advisable aggregate leverage fits in the interval, which should be specifically assessed for each entity, and can be determined by official reporting data through the proposed formulae. Managing common stockholders’ risk pursues to maintain the aggregate leverage ratio within its maximum and minimum. This task can be solved by modifying the structure and ratio of fixed and variable costs.

The Frozen Supply Chain Business Case: A Management Accounting Instructional Resource

This case guides students through the process of preparing a real-life business case. The business case involves capital expenditure analysis for a potential project in the Wally-Mart Supermarkets frozen supply chain. There are three parts to the business case: (1) prepare a financial model in Excel with a discounted cash flow method, to analyze relevant incremental capital expenditures, revenues, costs and profits; (2) concisely communicate the financial model and business case in a business style Word report, and (3) concisely communicate the financial model and business case in a business style PowerPoint presentation. The case materials include a practice financial modeling exercise. The case is suitable for use in undergraduate and graduate management accounting courses.

Financial modeling trends for production companies in the context of Industry 4.0

Over the years, technological progress has accelerated highly, and the speed, flexibility, human error reduction, and the ability to manage the process in real time have become more critical and required production companies to adapt production and business models according to the needs. The demand for real-time decision support systems adapted to these raising business needs is continuously growing. Nevertheless, businesses usually face challenges in identifying new indicators, data sources, and appropriate financial modeling methods to analyze them. This paper aims to define and summarize the main financial/economic forecasting methods for production companies in the context of Industry 4.0. Main findings show forecasting accuracy of up to 96% when combining economic and demand information, optimal forecasting period from 10 months to five years, more frequent use of soft indicators in forecasting, the relationship between company’s size and production planning. Four groups of indicators used in financial modeling, such as (I) production-related, (II) customers’ and demand-oriented, (III) industry-specific, and (IV) media information indicators, were separated. The analysis forms a suggestion for decision-makers to pay more attention to the forecasting object identification, indicators’ selection peculiarities, data collection possibilities, and the choice of appropriate methods of financial modeling. AcknowledgmentThis work was partly supported by Project No. 0121U100470 “Sustainable development and resource security: from disruptive technologies to digital transformation of Ukrainian economy”.