A Chaotic Approach on Solar Irradiance Forecasting

Fathima, T. A.; Nedumpozhimana, Vasudevan; Lee, Yee Hui; Dev, Soumyabrata

doi:10.1109/piers-fall48861.2019.9021305

Cited by 10 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result of its complexity and importance, financial time series prediction necessitates the development of more advanced and sophisticated hybrid algorithms. Chaos theory suggested a new way of modelling a deterministic complex system's underlying non-linear dynamic behaviour by a given scalar FTS using parameters such as the lag and integration incorporated in their respective phase spaces, where lag represents time delay and integration dimension means the number of variables necessary for the nonlinear dynamics of chaotic system [8,9]. The implementation of deep neural network methods can be useful to achieve greater accuracy of prediction [10,11].…”

Section: Introductionmentioning

confidence: 99%

“…Thus, in relation to the LSTM norm in compliance with the performance measures, Chaos+LSTM could not easily forecast. Figure(9) represents that the hybrid model's predictions of the test set of Crude Oil prices (USD). The results of the test set of crude oil price (USD) predictions are the slightly lower rate of values by the present models compared with the proposed models.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Statistical Evaluation and Prediction of Financial Time Series Using Hybrid Regression Prediction Models

Durairaj¹,

Mohan²

2021

ijisae

View full text Add to dashboard Cite

Financial time series are chaotic by nature, which makes prediction difficult and complicated. This research employs the new hybrid model for the prediction of FTS which comprises Long Short-Term Memory (LSTM), Polynomial Regression (PR), and Chaos Theory. First of all, FTS is tested for the presence of chaos, in this hybrid model. Later, using Chaos Theory, the time series is modelled with the chaos existence. The model time series will be entered in LSTM for initial forecasts. The sequence of errors derived from LSTM forecasts is PR appropriate for error predictions. Error forecasts and original model forecasts are applied to produce the final hybrid model forecasts. Performance testing of the hybrid model (Chaos+LSTM+PR) is conducted using three categories namely foreign exchange, commodity price and stock-market indices. The hybrid model proposed in this study, in compliance with MSE, Dstat and Theil's U, is proved superior to the individual models like ARIMA, Prophet, LSTM and Chaos+LSTM. The execution of these various hybrid proposed methods is done mainly using Python, additionally, the authors used Gretl® and R for some methods respectively. Ultimately, the final result of this hybrid model describes with a better result than the existing prediction models and it is proved using various types of FTS like Foreign exchange rates, commodity prices, and stock market indices respectively. Hence, the result shows that the proposed hybrid models of Chaos+LSTM+PR achieved with better prediction rate than the existing models on the nine datasets executed.

show abstract