Fond indekslarining realizatsiya qilingan volatillikni o‘ta tasodifiy daraxtlar algoritmi yordamida prognozlash: giperparametrlarning ablation-tadqiqoti
Qabul qilingan: 2026-07-18
Nashr etilgan: 2025-06-29
Annotatsiya
Mazkur ishda o‘ta tasodifiy daraxtlar algoritmining (ExtraTreesRegressor) uchta asosiy giperparametri — bazaviy daraxtlar soni N, maksimal chuqurlik max_depth va bargdagi minimal kuzatuvlar soni min_samples_leaf — ning fond indekslari va aksiyalar realizatsiya qilingan volatilligini k = 5 savdo kuni ufqida prognozlash sifatiga ta’siri tizimli ravishda tadqiq etilgan. Tajribalar to‘rtta instrument (AAPL, TSLA, ^GSPC, ^IXIC) bo‘yicha 11 yillik kunlik savdo tarixi (2015–2026) va K = 22 kengayuvchi qatlamli expanding-window walk-forward protokoli asosida amalga oshirilgan. 13 ta noyob ExtraTrees konfiguratsiyasi (jami 1144 ta mustaqil ishga tushirish) asosida quyidagilar aniqlangan: N qiymatini 100 dan yuqoriga oshirish RMSE ko‘rsatkichining juda kichik kamayishiga olib keladi, biroq o‘qitish vaqti 10 baravar ortadi; max_depth = 6–9 chegarasi eng kichik RMSE ni ta’minlaydi, bu esa kuchli shovqinli maqsadli o‘zgaruvchi sharoitida bias–variance muvozanatini aks ettiradi; min_samples_leaf parametrini 5 dan 50 gacha oshirish barglarni regularizatsiya qilish hisobiga RMSE ni monoton tarzda 11–16 % ga kamaytiradi. Eng yaxshi konfiguratsiya ^GSPC indeksi uchun RMSE = 0.00403 natijani ko‘rsatdi, bu LightGBM (0.00392) va XGBoost (0.00403) modellari bilan taqqoslanadigan darajadadir. Olingan natijalar kunlik chastotadagi ma’lumotlar asosida volatillikni prognozlash uchun giperparametrlarni tanlash bo‘yicha amaliy tavsiyalarni taqdim etadi. Kalit so‘zlar: realizatsiya qilingan volatillik; o‘ta tasodifiy daraxtlar; ExtraTrees; volatillikni prognozlash; ablation-tadqiqot; fond indekslari; walk-forward kross-validatsiya; moliya uchun mashinali o‘qitish.
Kalit so‘zlar
Adabiyotlar ro'yxati
-
Andersen T.G., Bollerslev T., Diebold F.X., Labys P. The distribution of realized exchange rate volatility // Journal of the American Statistical Association. — 2001. — Vol. 96(453). — P. 42–55.
-
Geurts P., Ernst D., Wehenkel L. Extremely randomized trees // Machine Learning. — 2006. — Vol. 63(1). — P. 3–42.
-
Breiman L. Random Forests // Machine Learning. — 2001. — Vol. 45(1). — P. 5–32.
-
Chen T., Guestrin C. XGBoost: A scalable tree boosting system // Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. — 2016. — P. 785–794.
-
Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T.-Y. LightGBM: A highly efficient gradient boosting decision tree // Advances in Neural Information Processing Systems (NeurIPS). — 2017. — Vol. 30. — P. 3146–3154.
-
Gu S., Kelly B., Xiu D. Empirical asset pricing via machine learning // Review of Financial Studies. — 2020. — Vol. 33(5). — P. 2223–2273.
-
Fischer T., Krauss C. Deep learning with LSTM for financial market predictions // European Journal of Operational Research. — 2018. — Vol. 270(2). — P. 654–669.
-
Sezer O.B., Gudelek M.U., Ozbayoglu A.M. Financial time series forecasting with deep learning: A systematic literature review // Applied Soft Computing. — 2020. — Vol. 90. — Art. 106181.
-
Lo´pez de Prado M. Advances in Financial Machine Learning. — Hoboken: Wiley, 2018. — 395 p.
-
Hamilton J.D. Time Series Analysis. — Princeton University Press, 1994. — 799 p.
-
Tsay R.S. Analysis of Financial Time Series. — 3rd ed. — Hoboken: Wiley, 2010. — 720 p.
-
Friedman J.H. Greedy function approximation: a gradient boosting machine // Annals of Statistics. — 2001. — Vol. 29(5). — P. 1189–1232.
-
Pedregosa F., Varoquaux G., Gramfort A. et al. Scikit-learn: Machine learning in Python // Journal of Machine Learning Research. — 2011. — Vol. 12. — P. 2825–2830.
-
Efron B., Tibshirani R.J. An Introduction to the Bootstrap. — New York: Chapman & Hall, 1993. — 436 p.
-
Engle R.F. Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation // Econometrica. — 1982. — Vol. 50(4). — P. 987–1007.
Mualliflar haqida
Litsenziya
This work is licensed under a Creative Commons Attribution 4.0 International License.