Forecasting the Profitability of Financial Instruments: Using Interactive Modeling and Visualization Tools

The article is devoted to the issues of automating the forecasting of the profitability of financial instruments by developing tools for interactive management of the parameters of stochastic models of profitability, calculations and visualization of results using the R programming language and the Shiny library. The purpose of the study is to create a web application that allows the User to manage all the key indicators affecting the final value of a financial instrument, to fine-tune the model by which the profitability trajectories will be built. To demonstrate the relationship of a particular model parameter to the final financial result, a graphical interpretation of the calculations is implemented, which allows real-time evaluation of the model’s response to a change in any parameter. The geometric Brownian motion model and the Monte Carlo method were used as a mathematical basis for building the web application. The research methodology is based on the use of mathematical modeling methods for forecasting asset prices under uncertainty. The main focus of the application is on interactive visualization of simulation results as a response to changes in the User interface parameters. This approach allows the user to work with the model parameters in real time, monitoring and controlling the system’s response to all of their actions. The application also implements functions for assessing possible scenarios for changing the value of assets, taking into account volatility, expected profitability, and a number of other characteristics. The results obtained during the development and practical use of the application show a high degree of control over the model’s behavior using visual elements of the application interface, clarity of presentation in assessing the expected profitability, and the ability to adapt the model to various financial instruments. The scenario options embedded in the application demonstrate how any minor changes in the input parameters affect the observed asset indicators, which emphasizes the importance of interactive stochastic analysis in the process of making investment decisions. The results of the study can be used for educational purposes to study tools for quantitative risk and profitability assessment, as well as in investment analysis. The developed application demonstrates the encapsulation of complex mathematical methods and concepts, make available for the User with clear and intuitive visual tools for studying financial risks and forecasting asset profitability.

1. Lukyanov P. B., Melekhina T. L. Visualization of research results using the example of dynamic assessment of national goal indicators. Samoupravleniye. 2022;5(133):42–45. (In Russ.). URL: https://elibrary.ru/rraimr

2. Lukyanov P. B. Interactive modeling of economic losses in planning feed mixtures. Information-measuring and Control Systems. 2023;21(6):38–47. (In Russ.). DOI: 10.18127/j20700814–202306–05

3. Lukyanov P. B. Development of tools for assessing and measuring losses associated with imbalances in feeding farm animals. Soft measurements and calculations. 2023;72(11–1):5–14. (In Russ.). DOI: 10.36871/2618–9976.2023.11.001

4. Buckner D., Dowd K., Hulley H. Arbitrage problems with reflected geometric Brownian motion. Finance and Stochastics. 2024;(28):1–26. DOI: 10.1007/s00780–023–00525-x

5. Fathi Vajargah K., Shoghi M. Simulation of Stochastic differential equation of geometric Brownian motion by quasi-Monte Carlo method and its application in prediction of total index of stock market and value at risk. Mathematical Sciences. 2015;(9):115–125. DOI: 10.1007/s40096–015–0158–5

6. Graf S., Korn R. A guide to Monte Carlo simulation concepts for assessment of risk-return profiles for regulatory purposes. European Actuarial Journal. 2020;(10):273–293. DOI: 10.1007/s13385–020–00232–3

7. Vardomatskaya E. Yu., Asobleva P. S. Monte-Carlo Simulation of Investment Risks. Materials and Technologies Journal. 2022;(1):50–57. (In Russ.). DOI: 10.24412/2617–149X‑2022–1–50–57

8. Buslenko N. P., Golenko D. I., Sobol I. M., Sragovich V. G., Shreider Yu. A. Method of statistical tests (Monte Carlo), Moscow: Fizmatgiz; 1962. 332 p. (In Russ.). URL: https://elibrary.ru/zgemdt

9. Myasoedova V. A. Comparison of technologies for creating interactive web applications using Dash and Shiny as an example. Modern Science. 2021;(1–1):479–482. (In Russ.). URL: https://elibrary.ru/wkbkbi

10. Combs P., Erickson J., Hsieh Ju.H., Guo K., Nolte S., Schmitt Ch., Auerbach S., Hur Ju. Tox21enricher-shiny: An R shiny application for toxicity functional annotation analysis. Frontiers in toxicology. 2023;5. DOI: 10.3389/ftox.2023.1147608

11. Sanz S., Kreitchmann R. S., Nájera P., Moreno J. D., Martínez-Huertas J.A., Sorrel M. A. Foco: A shiny app for formative assessment using cognitive diagnosis modeling. Psicologia educative. 2023;29(2):149–158.