نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد، دانشکده مالی، دانشگاه خاتم، تهران، ایران.

2 کارشناسی، گروه حسابداری، واحد اسلامشهر، دانشگاه آزاد اسلامی، تهران، ایران.

3 دانشجوی دکتری، گروه مدیریت مالی، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.

چکیده

یکی از مهم ترین مفاهیم در هر اقتصادی استارتاپها هستند زیرا آنها ویژگیها و شاخصههایی مانند نوآوری، ایجاد اشتغال، افزایش بهرهوری اقتصادی و ... دارند که آنها را از سایر شرکتها متمایز میکنند. بنابراین، شناخت بهتر آنها و آشنایی با جریانات درآمدی و ارزشگذاری آنها حائز اهمیت است. در این مقاله، تلاش کردهایم تا نقش مهم استارتاپها در اقتصاد، ویژگیها، اهداف اصلی و ... آنان را مطالعه کنیم. هدف اصلی این مقاله، پیشبینی بازدهی استارتاپ با استفاده از روشهای مبتنی بر هوش مصنوعی مانند الگوریتم ژنتیک (GA) و شبکه عصبی مصنوعی (ANN) است.  برخی شاخصهای جهانی مانند شاخص S&P500، شاخص DJIA و نماگرهای اقتصادی از جمله بازده 10ساله اوراق بهادار خزانه، شاخص مجموع بازار Wilshire5000 به همراه برخی نماگرهای ویژه دیگر در استارتاپها مانند تیم، ایده، زمانبندی و ... به عنوان متغیرهای ورودی مورد استفاده قرارگرفتهاند. از الگوریتم ژنتیک به عنوان انتخاب ویژگی و انتخاب مهمترین متغیرها استفاده گردیده است. از شبکه عصبی مصنوعی به عنوان مدلی جهت بهینهسازی و پیشبینی بازدهی استارتاپ استفاده گردیده است. از مدلهای اقتصادسنجی مانند تحلیل رگرسیون نیز استفاده کردهایم. مدلهای ارزش در معرض ریسک (VaR) و ارزش در معرض ریسک شرطی (C-VaR) را برای پورتفوی مورد نظر شامل سه استارتاپ (شرکت عام) دراپ باکس (DBX)، اسکوت24 (G24.DE) و تی آی ای (TIE.AS) تخمین زدهایم و پورتفوی بهینه را تشکیل دادهایم. نتایج نشان میدهد که روشهای مبتنی بر هوش مصنوعی در پیشبینی بازدهی استارتاپ قدرتمندتر هستند. از سویی دیگر، مدلهای VaR و C-VaR رهیافتهایی مفید در کمینهسازی ریسک و بیشینهسازی بازدهی هستند. در این مقاله دریافتیم که مدلهای مبتنی بر هوش مصنوعی دارای قدرت پیشبینی بالا و قابلیتهایی مانند افزایش سرعت محاسبات، بهبود نتایج براساس یادگیری، عدم وجود مفروضات محدودکننده، سهولت بکارگیری و ... هستند. اما، مدلهای اقتصادی دارای برخی ویژگیها و مفروضات محدودکننده مانند فرض نرمال بودن، خطی بودن، مانایی و ... هستند.
 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Forecasting Startup Return using Artificial Intelligence Methods and Econometric Models and Portfolio Optimization Using VaR and C-VaR

نویسندگان [English]

  • Milad Shahvaroughi Farahani 1
  • Amirhossein Esfahani 2
  • Mohammadreza Nejad Falatouri Moghaddam 3
  • Ali Ramezani 3

1 M.A, Faculty of Finance, Khatam University, Tehran, Iran.

2 B.A, Department of Accounting, Islamshahr Branch, Islamic Azad University, Tehran, Iran.

3 Ph.D student, Department of Financial Management, Science and Research Unit, Islamic Azad University, Tehran, Iran.

چکیده [English]

One of the main concepts in every economy are startups because they have some characteristics and qualifications such as innovation, job creation, boosting economic productivity and etc. that differentiate them from other companies. So, it is important to better identify them and make familiar with their revenue generations and valuations. In this paper, we have tried to study the main role of startups in economy, their characteristics, main goals and etc. The main goal of article is prediction of startup's return using artificial intelligence methods such as genetic algorithm (GA) and artificial neural network (ANN). There are multiple startup valuation models such as Berkus model, DCF model, venture capital method and etc. Since, there is not any information about startups such as sale, market size, profit and etc. and most of the models works with database, so, we have tried to analyze startups that are in stock markets and passed IPO stage. Some global indices such as S&P500, DJAI, and economic indicators such as 10 years Treasury yield, Wilshire 5000 Total Market Full Cap Index along with some other special indicators in startups like team, idea, timing and etc. are used as input variables. GA is used as feature selection and finding the most important variables. ANN is used as an optimization model and prediction of startup's returns. We used econometric models such as regression analysis. We have estimated Value at risk (VaR) and Conditional Value at risk (C-VAR) for considered portfolios including three startups (public company) such as Dropbox, Inc. (DBX), Scout24 SE (G24.DE) and TIE.AS and optimal portfolio formation. The results show that AI based methods are more powerful in prediction of startup's return. On the other hand, VaR and C-VaR models are very beneficial approach in minimizing risk and maximizing return. We found that artificial intelligence based models having high predictability and qualifications such as speed up calculations, improve by training, no assumption, ease of use and etc. But econometric models have some qualifications and assumptions such as normality, linearity, stationarity and etc. which are the limitation.

کلیدواژه‌ها [English]

  • Keywords: Artificial Neural Network (ANN)
  • Genetic Algorithm (GA)
  • Econometric Models
  • Startup valuation
  • Value at Risk and Conditional Value at Risk (VaR &
  • C-VaR)
Agatonovic-Kustrin, S., & Beresford, R. (2000). Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. Journal of pharmaceutical and biomedical analysis, 22(5), 717-727.
Akkaya, M. (2020). Startup valuation: Theories, models, and future. In Valuation Challenges and Solutions in Contemporary Businesses (pp. 137-156). IGI Global.
Baltagi, B. H. (2011). What Is Econometrics? In Econometrics (pp. 3-12). Springer, Berlin, Heidelberg.
Bjørnskov, C., & Foss, N. J. (2016). Institutions, entrepreneurship, and economic growth: what do we know and what do we still need to know? Academy of Management Perspectives, 30(3), 292-315.
Boudieb, D., Mohammedi, K., Bouziane, A., & Smaili, Y. (2011). OPTIMIZATION TECHNIQUES BY DARWIN'S THEORY OF EVOLUTION. International Journal of Arts & Sciences, 4(19), 131.
Chatterjee, S., & Hadi, A. S. (2013). Regression analysis by example. John Wiley & Sons.
de Oliveira, F. B., & Zotes, L. P. (2018). Valuation methodologies for business startups: a bibliographical study and survey. Brazilian Journal of Operations & Production Management, 15(1), 96-111.
DeJong, K. Analysis of the Behavior of a Class of Genetic Adaptive. Ph.D. Thesis, University of Michigan, Ann Arbor, MI, USA, 1975.
Dhochak, M., & Doliya, P. (2020). Valuation of a startup: Moving towards strategic approaches. Journal of Multi‐Criteria Decision Analysis, 27(1-2), 39-49.
Edison, H. (2020). Lean Internal Startups: Challenges and Lessons Learned. In Fundamentals of Software Startups (pp. 251-268). Springer, Cham.
Hidayat, S. E., Bamahriz, O., Hidayati, N., Sari, C. A., & Dewandaru, G. (2021). Value drivers of startup valuation from venture capital equity-based investing: A global analysis with a focus on technological factors. Borsa Istanbul Review.
Hsu, D. K., Haynie, J. M., Simmons, S. A., & McKelvie, A. (2014). What matters, matters differently: a conjoint analysis of the decision policies of angel and venture capital investors. Venture Capital, 16(1), 1-25.
Hyrkäs, A. (2016). Startup complexity: tracing the conceptual shift behind disruptive entrepreneurship. Publications of the Faculty of Social Sciences.
Jedlickova, M., & Kutnar, P. (2017, October). Construction of a fuzzy model for the success prediction of hi-tech companies with a short history. In International Conference at Brno University of Technology, Faculty of Business and Management.
Laitinen, E. K. (2019). Discounted Cash Flow (DCF) as a measure of startup financial success.
Lavanchy, M., Reichert, P., & Joshi, A. (2022). Blood in the water: An abductive approach to startup valuation on ABC's Shark Tank. Journal of Business Venturing Insights, 17, e00305.
Magalhães, R. P. C. (2019). What is a startup? a scoping review on how the literature defines startup (Doctoral dissertation).
Montani, D., Gervasio, D., & Pulcini, A. (2020). Startup company valuation: The state of art and future trends. International Business Research, 13(9), 31-45.
Rahardjo, D., & Sugiarto, M. (2019, March). Valuation model using a mixed real options method: a review on Singapore and Indonesia digital startups. In 16th International Symposium on Management (INSYMA 2019) (pp. 9-12). Atlantis Press.
Salamzadeh, A., & Kawamorita Kesim, H. (2015). Startup companies: Life cycle and challenges. In 4th International conference on employment, education and entrepreneurship (EEE), Belgrade, Serbia.
Schückes, M., & Gutmann, T. (2021). Why do startups pursue initial coin offerings (ICOs)? The role of economic drivers and social identity on funding choice. Small Business Economics, 57(2), 1027-1052.
Shariatpanahi, S. M., Amiri, M., Babajani, J., Taghavi Fard, M. T., & Khalili, E. (2020). Model Determination for Equilibrium Valuation of Startup Companies Using Real Option Method in the Presence of Agency Cost. Financial Research Journal, 22(2), 182-205.
Shestakov, D. (2021). The Hypotheses Testing Method for Evaluation of Startup Projects. Journal of Economics and Management Sciences, 4(4), p47-p47.
Wang, M. H. (2017). Artificial Intelligence and Subfields. Santa Clara University, Department of Computer Engineering.