Subject. Investment activity and management decision?making processes in the high?tech segment of e?commerce. Objectives. Comprehensive development and modernization of qualitative and quantitative methods for substantiating investment projects in e?commerce, taking into account the specifics of the digital environment and the high volatility of markets. Methods. The study applies methods of logical, systemic and comparative analysis. It uses adapted strategic management models, upgraded corporate finance metrics, as well as stochastic modelling and predictive tools of machine learning. Results. The fundamental limitations of traditional deterministic models from the industrial era are substantiated when applied to high?tech projects. A qualitatively new approach to the selection of investment initiatives has been developed, based on a digital readiness matrix. A system of specific financial indicators is proposed, and the necessity of implementing probabilistic models (fuzzy real options) and artificial intelligence algorithms (ensemble methods) for predictive assessment of unit economics and hedging of extreme risks is demonstrated. Conclusions. Adequate assessment of investments in the e?commerce segment requires a shift from static linear extrapolation to stochastic analysis based on big data. The implementation of the developed modified approaches moves the investment decision?making process into the realm of data analytics, enabling corporate management to avoid cash flow gaps and properly evaluate managerial flexibility.
Keywords: investment analysis, e-commerce, machine learning, unit economics, real options
References:
Bukht R., Hicks R. [Defining, conceptualising and measuring the digital economy]. Vestnik mezhdunarodnykh organizatsii: obrazovanie, nauka, novaia ekonomika, 2018, vol. 13, no. 2, pp. 143–172. (In Russ.) EDN: YXBNWX
Kandiev S.S. [Electronic commerce: features and development trends]. Molodoi uchenyi, 2023, no. 1, pp. 76–81. (In Russ.) EDN: VZQDHM
Demchenko S.K. [E‑commerce risks: Sources and mitigations]. Ekonomika i upravlenie innovatsiyami, 2021, no. 4, pp. 16–26. (In Russ.) DOI: 10.26730/2587‑5574‑2021‑4‑16‑26 EDN: CAXXLH
Damodaran A. Investitsionnaia otsenka: instrumenty i metody otsenki lyubykh aktivov [Investment valuation: Tools and techniques for determining the value of any asset]. Moscow, Al’pina Publ., 2026, 1339 p.
Stepnov I.M., Koval’chuk Yu.A. [Investment valuation of modern business models]. Analiz. Audit, 2021, vol. 8, no. 2, pp. 12–23. (In Russ.) DOI: 10.26794/2408‑9303‑2021‑8‑2‑12‑23 EDN: HFECFQ
Smirnov A., Tul’bovich E. [Strategy and economics of IT]. Upravlencheskii uchet i byudzhetirovanie, 2008. URL: Link (In Russ.)
Nag A. Enhancing DCF and LBO Models with Machine Learning Forecasts, 2025. DOI: 10.13140/RG.2.2.22011.17444/1
Nigai E.A. [Customer lifetime value (LTV) management in business activities: assessment methods and strategic decision‑making aspects]. Territoriia novykh vozmozhnostei. Vestnik Vladivostokskogo gosudarstvennogo universiteta, 2024, vol. 16, no. 3, pp. 54–65. (In Russ.) EDN: SZICAH
Chachis D.Yu. [Forecasting customer LTV: methods and practical application]. Vestnik nauki, 2025, vol. 2, no. 4, pp. 767–771. (In Russ.) EDN: GZEBEV
Hull J.C. Optsiony, f’yuchersy i drugie proizvodnye finansovye instrumenty [Options, futures, and other derivatives]. Moscow, Vil’yams Publ., 2014, 1070 p.
Baranov A.O., Muzyko E.I., Pavlov V.N. Otsenka effektivnosti innovatsionnykh proektov s ispol’zovaniem optsionnogo i nechetko‑mnozhestvennogo podkhodov [Evaluation of the effectiveness of innovative projects using real options and fuzzy‑sets approaches]. Novosibirsk, IEOPP SO RAN Publ., 2018, 335 p. (In Russ.)
Bawack R.E., Wamba S.F., Carillo K.D.A., Akter S. Artificial intelligence in E‑Commerce: A bibliometric study and literature review. Electronic Markets, 2022, vol. 32, pp. 297–338. DOI: 10.1007/s12525‑022‑00537‑z
Khitrova E.M., Proshutinskaia S.S. [Artificial intelligence and machine learning in supporting investment decisions based on expert data]. Izvestiia Baikal’skogo gosudarstvennogo universiteta, 2025, vol. 35, no. 2, pp. 217–227. (In Russ.) DOI: 10.17150/2500‑2759.2025.35(2).217‑227 EDN: QMIMAT
Molchanova R.V. [Application of machine learning in internet marketing]. Mezhdunarodnyi nauchno‑issledovatel’skii zhurnal, 2024, no. 4. (In Russ.) DOI: 10.23670/IRJ.2024.142.113
Bidgoli M.R., Vanani I.R., Goodarzi M. Predicting the success of startups using a machine learning approach. Journal of Innovation and Entrepreneurship, 2024, vol. 13. DOI: 10.1186/s13731‑024‑00436‑x
Balaji S., Manikavelan D. Enhancing E‑Commerce Predictive Analytics using Ensemble Models for Consumer Behaviour and Market Forecasting. In: International Conference on Intelligent Systems and Computational Networks (ICISCN), Bidar, India, 2025, pp. 1–7. DOI: 10.1109/ICISCN64258.2025.10934325
Sayyad J.K., Attarde K., Saadouli N. Optimizing e‑Commerce Supply Chains With Categorical Boosting: A Predictive Modeling Framework. IEEE Access, 2024, vol. 12, pp. 134549–134567. DOI: 10.1109/ACCESS.2024.3447756
Liu Y., Lei F., Huangcheng W. Design and Implementation of Cross‑border E‑commerce Risk Control System Based on Machine Learning Algorithm and Computer Simulation. In: 7th International Conference on Computer Information Science and Artificial Intelligence (CISAI 2024), Shaoxing, China, ACM, New York, NY, USA, 2024, 6 p. DOI: 10.1145/3703187.3703217
Davidor S., Dako O., Nwachukwu P. et al. An AI‑Enabled Valuation Framework for Digital Transformation in Investment Banking. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2024, vol. 10, iss. 4, pp. 978–1004. DOI: 10.32628/CSEIT251134103
