Using statistical analysis to evaluate enterprise performance in the Python programming environment

   The relevance of the conducted research consists of assessing the activities of a manufacturing enterprise using statistical tools and interpreting numerical financial indexes in the modern programming language Python.

   The use of libraries embedded in the software, as well as the use of statistical calculations in the final format of interactive graphs, made it possible to interpret reliable information about the activities of the enterprise, as well as predict profit (loss) for the next few years. This method of calculation is necessary primarily for enterprise management to plan activities taking into account external economic conditions, as well as possible unforeseen circumstances and emerging situations. The software clearly demonstrates the possible representation of the dynamics and trends in the development of business entities in a concise and understandable, strictly formulated, accurate statistical and mathematical form. Analysis of the activities of various enterprises helps to identify their contribution to the development of the economy of the regions and the country as a whole, therefore the development of scientifically based recommendations to improve the efficiency of their activities and ensure sustainable development is a very relevant research topic at present.

   Purpose of the study. Study of the activities of the LLC “Omsk Polypropylene Plant” enterprise for 2019–2023 using statistical tools and Python software libraries. As well as forecasting the main financial indexes for the coming years, taking into account the interpretation of the values obtained as a result of using the web development environment in numerical, tabular and graphical forms.

   Description and forecasting of the development prospects of an enterprise based on accurate performance data are necessary not only for the managers of the enterprises under review, but also for their shareholders.

   Materials and methods. The research materials used were regulatory documents, scientific publications of Russian and foreign authors, and accounting (financial) reporting data. The scientific article used the main research methods: monographic, comparative analysis, classification and generalization. The main methods of statistical and economic analysis were descriptive statistics, inferential statistics, regression analysis, time series analysis, etc.

   Results. Derived statistical quantities using packages embedded in Python software such as Pandas, Seaborn, Matplotlib, NumPy, skleaern, Linear_model, LinearRegression, Scikit-learn, Metrics, Model selection. The following describes statistical indexes on visually programmed graphs; all data are entered into the Python web development environment using an auxiliary package of tables made in MS Excel. The presented calculations will not only allow timely and promptly react to changes in the external economic environment of activity, but also adjust costs to already predicted values, which, in turn, will help to increase the profitability of the enterprise, which is the main task of any owner.

   Conclusion. Based on the results of the study, the authors developed forecast values of profit (loss) for LLC “Omsk Polypropylene Plant” and gave recommendations for improving the efficiency of the enterprise in the coming years.

1. Gosudarstvennyy informatsionnyy resurs bukhgalterskoy (finansovoy) otchetnosti = State information resource of accounting (financial) reporting. [Internet]. Federal Tax Service. Available from: https://bo.nalog.ru/ (In Russ.)

2. Inflyatsiya v Rossii = Inflation in Russia [Internet]. GoGov.ru. Available from: https://gogov.ru/articles/inflation-rf (In Russ.)

3. Karyshev M.Yu., Gerasimova E.A. Information technologies as a tool for assessing the effectiveness and a factor in the development of the digital economy. Vestnik SamGUPS = Bulletin of Samara State University of Railways. 2021; 4: 19–26. (In Russ.)

4. Klyuchevaya stavka i stavka refinansirovaniya = Key rate and refinancing rate. [Internet]. GARANT. Available from: https://base.garant.ru/10180094. (In Russ.)

5. Konyukova O.G., Lukash A.N. Application of economic and statistical methods to improve the efficiency of cinemas under sanctions. Statistika i Ekonomika = Statistics and Economics. 2024; 21; 4: 35-44. (In Russ.)

6. Lagutin M.B., Budilova E.V., Migranova L.A. Dynamics. Naseleniye = Population. 2015; 3: 93. (In Russ.)

7. Otsenka rezul’tatov lineynoy regressii = Evaluation of linear regression results. [Internet]. Habr. Available from: https://habr.com/ru/articles/195146. (In Russ.)

8. Pismenny D.T. Konspekt lektsiy po vysshey matematike: polnyy kurs = Lecture notes on higher mathematics: full course. 20^th ed. Moscow: AIRIS-press; 2024. 608 p. (In Russ.)

9. Prover’ sebya i kontragenta = Check yourself and your counterparty. [Internet]. Federal Tax Service. Available from: https://pb.nalog.ru. (In Russ.)

10. Salin V.N., Popova A.A., Shpakovskaya E.P. The place of statistics in globalization processes. Vek globalizatsii = The century of globalization. 2013; 2: 131-142. (In Russ.)

11. Federal Law “On Industrial Policy in the Russian Federation” dated 31. 12. 2014 No. 488-FZ (latest revision). [Internet]. ConsultantPlus. Available from: https://www.consultant.ru/document/cons_doc_LAW_173119. (In Russ.)

12. Coefficient of Variation. [Internet]. Resource Systems Consulting. Available from: https://www.resourcesystemsconsulting.com/2011/06/06/coefficient-of-variation/

13. Examples [Internet]. Matplotlib. Available from: https://matplotlib.org/stable/gallery/index.html

14. Hisashi Kobayashi, Brian L., Mark and William Turin. Probability, Random Processes, and Statistical Analysis Applications to Communications, Signal Processing, Queuing Theory and Mathematical Finance. New York: Cambridge University Press; 2012. 813 p.

15. Kalnitskaya I.V., Konyukova O.G. Liquidity of the organization’s assets: problems of assessment and directions of their solution. Journal of Siberian Federal University. Humanities & Social Sciences. 2024. 17(3): 445–456.

16. Patlasov O. Yu., Konyukova O. G. Model for assessing the financial position of oil and gas companies. Journal of Siberian Federal University. Humanities & Social Sciences. 2023. 16(3): 391–404.

17. Python, korrelyatsiya i regressiya: chast’ 1 = Python, Correlation, and Regression: Part 1. [Internet]. Habr. Available from: https://habr.com/ru/articles/557998. (In Russ.)

18. Python | Mean Squared Error. [Internet]. GeeksforGeeks. Available from: https://www.geeks-forgeeks.org/python-mean-squared-error/

19. Summary.lm: Summarizing Linear Model Fits. [Internet]. RDocumentation. Available from: https://www.rdocumentation.org/packages/stats/versions/3.6.2/topics/summary.lm

20. Supervised learning. [Internet]. Scikit-learn. Available from: https://scikit-learn.org/stable/supervised_learning.html

21. Variance and Standard Deviation. [Internet]. Newcastle University. Available from: https://www.ncl.ac.uk/webtemplate/ask-assets/external/maths-resources/statistics/descriptive-statistics/variance-and-standard-deviation.html