KaydedilenlerDerginizi ekleyin

Dergiler / Afyon Kocatepe Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi / 2024 / Cilt: 26 Sayı: Özel Sayı Özel Sayı

Belirsiz kriter ağırlıkları altında yeni bir ÇKKV yöntemi: Yapay zekâ sohbet robotlarına (ChatGPT4, Copilot, Gemini) dayalı portföy seçimi üzerine bir uygulama

A novel MCDM method under uncertain criteria weights: An application on portfolio selection based on artificial intelligence chatbots (ChatGPT4, Copilot, Gemini)

Furkan Göktaş
Fatih Güçlü
Sayfa
68–80
Yayın Tarihi
2024-10-21
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Yapılan uygulamada uzman bilgisi ya da geçmiş veri ile elde edilen sonuçlar arasında genellikle pozitif ama yüksek düzeyde olmayan ilişki olduğu bulunmuştur.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Çok kriterli karar verme (ÇKKV) problemlerinin en tartışmalı noktası kriter ağırlıklandırmadır.
📊
Temel Bulgular & Veri:Çünkü farklı kriter ağırlıkları genellikle farklı sonuçların ortaya çıkmasına neden olur.
💡
Sonuç & Katkı:Yapılan uygulamada uzman bilgisi ya da geçmiş veri ile elde edilen sonuçlar arasında genellikle pozitif ama yüksek düzeyde olmayan ilişki olduğu bulunmuştur.
🔬Tür:Araştırma Makalesi
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Çok kriterli karar verme · portföy seçimi · sürdürülebilirlik

Özet

Çok kriterli karar verme (ÇKKV) problemlerinin en tartışmalı noktası kriter ağırlıklandırmadır. Çünkü farklı kriter ağırlıkları genellikle farklı sonuçların ortaya çıkmasına neden olur. Bu çalışmanın amacı kriter ağırlıklarının belirsiz olduğu durumda ÇKKV problemlerini çözebilmek için yeni bir yöntem geliştirmektir. Bu kapsamda bu çalışmada Belirsiz Kriter Ağırlıklarıyla Olabilirlik Değerlendirme Sistemi (U-PES) önerilmiştir. Uzman bilgisinden (yapay zekâ sohbet robotlarından) ve geçmiş veriden yararlanılarak Borsa İstanbul’da işlem gören sekiz adet hisse senedi ile portföy oluşturmada U-PES kullanılmıştır. Buradaki kriterler; beklenen getiri, standart sapma ve Çevresel-Sosyal-Kurumsal Yönetim (ESG) bileşenleri olarak belirlenmiştir. Yapılan uygulamada uzman bilgisi ya da geçmiş veri ile elde edilen sonuçlar arasında genellikle pozitif ama yüksek düzeyde olmayan ilişki olduğu bulunmuştur.

Abstract

The most controversial aspect of multi-criteria decision-making (MCDM) problems is criteria weighting. Because different criteria weights generally lead to different results. This study aims to develop a new method for solving MCDM problems with uncertain criteria weights. In this context, we propose the Possibilistic Evaluation System with Uncertain Criteria Weights (U-PES) in this study. We use U-PES to form a portfolio with eight stocks listed in Borsa Istanbul using expert knowledge (artificial intelligence chatbots) and historical data. Here, we determine the criteria as expected return, standard deviation, and Environmental-Social-Governance (ESG) components. In the application, we observe generally positive but not high-level relationships between the results obtained with expert knowledge or historical data.

🔖

Bu Makaleye Atıf Yap

Göktaş, F., Güçlü, F. (2024). Belirsiz kriter ağırlıkları altında yeni bir ÇKKV yöntemi: Yapay zekâ sohbet robotlarına (ChatGPT4, Copilot, Gemini) dayalı portföy seçimi üzerine bir uygulama. Afyon Kocatepe Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, Cilt: 26 Sayı: Özel Sayı Özel Sayı, 68–80. https://doi.org/10.33707/akuiibfd.1454952

📄 Tam Metin PDF Okuyucu

↗Yeni Sekme

PDF belgesi yükleniyor...

Kaynakça (42)

  1. Ahangar, R. G. ve Fietko, A. (2023). Exploring the potential of ChatGPT in financial decision making. R. Gharoie Ahangar ve M. Napier (Ed.), Advances in Business Information Systems and Analytics içinde (ss. 94-111). IGI Global. https://doi.org/10.4018/978-1-6684-8386-2.ch005
  2. Akbaş, S. ve Erbay Dalkılıç, T. (2021). A hybrid algorithm for portfolio selection: An application on the Dow Jones Index (DJI). Journal of Computational and Applied Mathematics, 398, 113678. https://doi.org/10.1016/j.cam.2021.113678
  3. Aldridge, I. (2023). The AI revolution: From linear regression to ChatGPT and beyond and how it all connects to finance. The Journal of Portfolio Management, 49(9), 64-77. https://doi.org/10.3905/jpm.2023.1.519
  4. Altan, İ. M. ve Kılıç, M. (2023). Science fiction to real life: BING AI as an investment advisor. Ekonomi İşletme ve Yönetim Dergisi, 7(2), 240-260. https://doi.org/10.7596/jebm.31122023.003
  5. Bisht, K. ve Kumar, A. (2022). Stock portfolio selection hybridizing fuzzy base-criterion method and evidence theory in triangular fuzzy environment. Operations Research Forum, 3(4), 1-32. https://doi.org/10.1007/s43069-022-00167-3
  6. Bouslah, K., Liern, V., Ouenniche, J. ve Pérez‐Gladish, B. (2023). Ranking firms based on their financial and diversity performance using multiple‐stage unweighted TOPSIS. International Transactions in Operational Research, 30(5), 2485-2505. https://doi.org/10.1111/itor.13143
  7. Chen, Z., Zheng, L., Lu, C., Yuan, J. ve Zhu, D. (2023). ChatGPT informed graph neural network for stock movement prediction. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4464002
  8. Dubois, D. (2006). Possibility theory and statistical reasoning. Computational Statistics & Data Analysis, 51(1), 47-69. https://doi.org/10.1016/j.csda.2006.04.015
  9. Göktaş, F. ve Duran, A. (2019). A new possibilistic mean-variance model based on the principal components analysis: an application on the Turkish holding stocks. Journal of Multiple-Valued Logic & Soft Computing, 32(5-6), 455-476.
  10. Göktaş, F. ve Gökerik, M. (2024). A novel robust theoretical approach on social media advertisement platform selection. International Journal of Engineering Research and Development, 16(1), 373-382. https://doi.org/10.29137/umagd.1398580
  11. Göktaş, F. ve Güçlü, F. (2024). Yeni bir çok kriterli karar verme yaklaşımı “olabilirlik değerlendirme sistemi”: Katılım fonları üzerine bir uygulama. Black Sea Journal of Engineering and Science, 7(1), 1-8. https://doi.org/10.34248/bsengineering.1341340
  12. Grant, M. C. ve Boyd, S. P. (2008). Graph implementations for nonsmooth convex programs. In Recent advances in learning and control (pp. 95-110). Springer, London. https://doi.org/10.1007/978-1-84800-155-8_7
  13. Hair, J. F., Money, A. H., Samouel, P. ve Page, M. (2007). Research methods for business. Education+Training, 49(4), 336-337. https://doi.org/10.1108/et.2007.49.4.336.2
  14. He, Y., Romanko, O., Sienkiewicz, A., Seidman, R. ve Kwon, R. (2021). Cognitive user interface for portfolio optimization. Journal of Risk and Financial Management, 14(4), 180. https://doi.org/10.3390/jrfm14040180
  15. Karami, A. ve Johansson, R. (2014). Utilization of multi attribute decision making techniques to integrate automatic and manual ranking of options. Journal of Information Science and Engineering, 30(2), 519-534. https://doi.org/10.6688/JISE.2014.30.2.14
  16. Kim, J. H. (2023). What if ChatGPT were a quant asset manager. Finance Research Letters, 58, 104580. https://doi.org/10.1016/j.frl.2023.104580
  17. Ko, H. ve Lee, J. (2023). Can ChatGPT improve investment decision? From a portfolio management perspective. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4390529
  18. Li, H., Cao, Y. ve Su, L. (2022). Pythagorean fuzzy multi-criteria decision-making approach based on Spearman rank correlation coefficient. Soft Computing, 26(6), 3001-3012. https://doi.org/10.1007/s00500-021-06615-2
  19. Liern, V. ve Pérez-Gladish, B. (2022). Multiple criteria ranking method based on functional proximity index: Un-weighted TOPSIS. Annals of Operations Research, 311(2), 1099-1121. https://doi.org/10.1007/s10479-020-03718-1
  20. López-García, A., Liern, V. ve Pérez-Gladish, B. (2023). Determining the underlying role of corporate sustainability criteria in a ranking problem using UW-TOPSIS. Annals of Operations Research, 1-24. https://doi.org/10.1007/s10479-023-05543-8
  21. Lopez-Lira, A. ve Tang, Y. (2023). Can ChatGPT forecast stock price movements? Return predictability and large language models. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4412788
  22. Lu, F., Huang, L. ve Li, S. (2023). ChatGPT, generative AI, and investment advisory. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4519182
  23. Lutgens, F. ve Schotman, P. C. (2010). Robust portfolio optimisation with multiple experts. Review of Finance, 14(2), 343-383. https://doi.org/10.1093/rof/rfn028
  24. Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77-91. https://doi.org/10.2307/2975974
  25. Narang, M., Joshi, M. C. ve Pal, A. K. (2021). A hybrid fuzzy COPRAS-base-criterion method for multi-criteria decision making. Soft Computing, 25(13), 8391-8399. https://doi.org/10.1007/s00500-021-05762-w
  26. Oehler, A. ve Horn, M. (2024). Does ChatGPT provide better advice than robo-advisors? Finance Research Letters, 60, 104898. https://doi.org/10.1016/j.frl.2023.104898
  27. Okhrin, Y. ve Schmid, W. (2006). Distributional properties of portfolio weights. Journal of Econometrics, 134(1), 235-256. https://doi.org/10.1016/j.jeconom.2005.06.022
  28. Parkhid, M. ve Mohammadi, E. (2022). Bi-level portfolio optimization considering fundamental analysis in fuzzy uncertainty environments. Fuzzy Optimization and Modeling Journal, 3(3), 1-18. https://doi.org/10.30495/fomj.2022.1949729.1055
  29. Pelster, M. ve Val, J. (2024). Can ChatGPT assist in picking stocks? Finance Research Letters, 59, 104786. https://doi.org/10.1016/j.frl.2023.104786
  30. Pinochet, L. H. C., Moreira, M. Â. L., Fávero, L. P., Santos, M. D. ve Pardim, V. I. (2023). Collaborative work alternatives with ChatGPT based on evaluation criteria for its use in higher education: Application of the PROMETHEE-SAPEVO-M1 method. Procedia Computer Science, 221, 177-184. https://doi.org/10.1016/j.procs.2023.07.025
  31. Pośpiech, E. (2019). Effective portfolios – An application of multi-criteria and fuzzy approach. Folia Oeconomica Stetinensia, 19(1), 126-139. https://doi.org/10.2478/foli-2019-0009
  32. Romanko, O., Narayan, A. ve Kwon, R. H. (2023). ChatGPT-based investment portfolio selection. Operations Research Forum, 4(4), 1-27. https://doi.org/10.1007/s43069-023-00277-6
  33. Saaty, T. L., Rogers, P. C. ve Pell, R. (1980). Portfolio selection through hierarchies. The Journal of Portfolio Management, 6(3), 16-21. https://doi.org/10.3905/jpm.1980.408749
  34. Sanjib Biswas, Joshi, N. ve Jayanta Nath Mukhopadhyaya. (2023). ChatGPT in investment decision making: An introductory discussion. https://doi.org/10.13140/RG.2.2.36417.43369
  35. Souliotis, G., Alanazi, Y. ve Papadopoulos, B. (2022). Construction of fuzzy numbers via cumulative distribution function. Mathematics, 10(18), 3350. https://doi.org/10.3390/math10183350
  36. Svoboda, I. ve Lande, D. (2024). Enhancing multi-criteria decision analysis with AI: Integrating analytic hierarchy process and GPT-4 for automated decision support. https://doi.org/10.48550/arxiv.2402.07404
  37. Tanaka, H. ve Guo, P. (1999). Portfolio selection based on upper and lower exponential possibility distributions. European Journal of Operational Research, 114(1), 115-126. https://doi.org/10.1016/S0377-2217(98)00033-2
  38. Tiryaki, F. ve Ahlatçıoğlu, B. (2009). Fuzzy portfolio selection using fuzzy analytic hierarchy process. Information Sciences, 179(1-2), 53-69. https://doi.org/10.1016/j.ins.2008.07.023
  39. Ullah, R., Ismail, H. B., Islam Khan, M. T. ve Zeb, A. (2024). Nexus between ChatGPT usage dimensions and investment decisions making in Pakistan: Moderating role of financial literacy. Technology in Society, 76, 102454. https://doi.org/10.1016/j.techsoc.2024.102454
  40. Vafaei, N., Ribeiro, R. A. ve Camarinha-Matos, L. M. (2016). Normalization techniques for multi-criteria decision making: Analytical hierarchy process case study. In Doctoral Conference on Computing, Electrical and Industrial Systems (pp. 261-269). https://doi.org/10.1007/978-3-319-31165-4_26
  41. Vaidogas, E. R., Zavadskas, E. K. ve Turskis, Z. (2007). Reliability measures in multicriteria decision making as applied to engineering projects. International Journal of Management and Decision Making, 8(5-6), 497-518. https://doi.org/10.1504/IJMDM.2007.013414
  42. Yadav, S., Kumar, A., Mehlawat, M. K., Gupta, P. ve Charles, V. (2023). A multi-objective sustainable financial portfolio selection approach under an intuitionistic fuzzy framework. Information Sciences, 646, 119379. https://doi.org/10.1016/j.ins.2023.119379