Zaman Serisi Veri Kümeleri İçin Olasılığa Dayalı Tahmin Yöntemi

Bu makalede, zaman serisi veri kümelerini tahmin etmek için Çoklu Model Parçacık Filtresinin (ÇMPF) bir çeşidi olarak düşünülebilecek yeni bir olasılık tabanlı teknik kullanılmaktadır. Yöntemimizin güvenilirlik performansı art arda altmış günden oluşan sanal bir rastgele senaryo kullanılarak kanıtlanmıştır. İkinci, üçüncü ve dördüncü günde tahmin edilen durumlar ile gerçekte karşılık gelen değerler arasında büyük bir fark ortaya çıkmaktadır; yöntemimiz kullanılarak tahmin edilen durumlar gerçek değerlere doğru hızla yakınsarken, tek başına klasik bir lineer model kullanıldığında büyük miktarda sapma göstermektedir. Makalede yaklaşımımızın performansı; Kök-Ortalama-Kare Hatası, Ortalama Mutlak Yüzde Hatası ve Korelasyon Katsayısı performans değerlendirme ölçütleri dikkate alınarak; BIST (Borsa İstanbul Endeksi), TAIEX (Tayvan Borsa Endeksi), ve ABC (Avustralya Bira Tüketimi) zaman serisi veri kümelerine halihazırda uygulanmış olan diğer bazı tekniklerle karşılaştırılmaktadır.

Probabilistic-Based Forecasting Method For Time Series Datasets

In this paper, a new probabilistic technique (a variant of Multiple Model Particle Filter-MMPF) will be used to predict time-series datasets. At first, the reliable performance of our method is proved using a virtual random scenario containing sixty successive days; a large difference between the predicted states and the real corresponding values arises on the second, third, and fourth day. The predicted states that are determined by using our method converge rapidly towards the real values while a classical linear model exhibits a large amount of divergence if used alone here. Then, the performance of our approach is compared with some other techniques that were already applied to the same time-series datasets: IEX (Istanbul Stock Exchange Index), TAIEX (Taiwan Stock Exchange), and ABC (The Australian Beer Consumption). The performance evaluation metrics that are utilized here are the correlation coefficient, the mean absolute percentage error, and the root mean squared error.

___

  • [1] Q. Song and B. S. Chissom, “Forecasting enrollments with fuzzy time series—part ii,” Fuzzy Sets and Systems, vol. 54, pp. 1–9, 1993.
  • [2] F. B. Fitch, “Mcculloch warren s. and pitts walter. a logical calculus of the ideas immanent in nervous activity. bulletin of mathematical biophysics , vol. 5 (1943), pp. 115–133.” Journal of Symbolic Logic, vol. 9, pp. 49–50, 1944.
  • [3] J.-T. Tsai, P.-Y. Chou, and J.-H. Chou, “Color filter polishing optimization using anfis with sliding-level particle swarm optimizer,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 50, pp. 1193–1207, 2020.
  • [4] I. B. Tu¨rksen, “Fuzzy functions with lse,” Appl. Soft Comput., vol. 8, pp. 1178–1188, 2008.
  • [5] S. Beyhan and M. Alci, “Fuzzy functions based arx model and new fuzzy basis function models for nonlinear system identification,” Appl. Soft Com- put., vol. 10, pp. 439–444, 2010.
  • [6] N. Tak, “Type-1 recurrent intuitionistic fuzzy functions for forecasting,” Expert Syst. Appl., vol. 140, 2020.
  • [7] B. Ristic, S. Arulampalam, and N. J. Gordon, “Beyond the kalman filter: Particle filters for tracking applications,” 2004.
  • [8] J. Wu, Q. Fang, Y. Xu, J. Su, and F. Ma, “Kalman filter based time series prediction of cake factory daily sale,” 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1–7, 2017.
  • [9] C. Yang, W. Shi, and W. Chen, “Comparison of unscented and extended kalman filters with application in vehicle navigation,” Journal of Navigation, vol. 70, pp. 411 – 431, 2016.
  • [10] C. Pan, A. rong Huang, Z. He, C. Lin, Y. Sun, S. Zhao, and L. Wang, “Prediction of remaining useful life for lithium-ion battery based on particle filter with residual resampling,” Energy Science & Engineering, vol. 9, pp. 1115 – 1133, 2021.
  • [11] M. S. Arulampalam, S. Maskell, N. J. Gordon, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking,” IEEE Trans. Signal Process., vol. 50, pp. 174–188, 2002.
  • [12] X. Ping, Q. Chen, G. Liu, J. Su, and F. Ma, “Particle filter based time series prediction of daily sales of an online retailer,” 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1–6, 2018.
  • [13] M. Magris, M. Shabani, and A. Iosifidis, “Bayesian bilinear neural network for predicting the mid-price dynamics in limit-order book markets,” arXiv:2203.03613v1 [econ.EM], 7 2022.
  • [14] A. Baba, “Advanced ai-based techniques to predict daily energy consumption: A case study,” Expert Syst. Appl., vol. 184, p. 115508, 2021.
  • [15] S.-M. Chen and B. D. H. Phuong, “Fuzzy time series forecasting based on optimal partitions of intervals and optimal weighting vectors,” Knowl. Based Syst., vol. 118, pp. 204–216, 2017.
  • [16] S. A. Alam and O. Gustafsson, “Improved particle filter resampling architectures,” Journal of Signal Processing Systems, vol. 92, pp. 555–568, 2020.
  • [17] S.-M. Chen and W.-S. Jian, “Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups, similarity measures and pso techniques,” Inf. Sci., vol. 391, pp. 65–79, 2017.
Düzce Üniversitesi Bilim ve Teknoloji Dergisi-Cover
  • Yayın Aralığı: Yılda 4 Sayı
  • Başlangıç: 2013
  • Yayıncı: Düzce Üniversitesi Fen Bilimleri Enstitüsü