TSF - Two Stage Forecasting (TSF) for Long Memory Time Series in Presence of Structural Break

Forecasting of long memory time series in presence of structural break by using TSF algorithm by Papailias and Dias (2015) <doi:10.1016/j.ijforecast.2015.01.006>.

Last updated 8 years ago

2.20 score 32 scripts 126 downloads

WaveletArima - Wavelet-ARIMA Model for Time Series Forecasting

Noise in the time-series data significantly affects the accuracy of the ARIMA model. Wavelet transformation decomposes the time series data into subcomponents to reduce the noise and help to improve the model performance. The wavelet-ARIMA model can achieve higher prediction accuracy than the traditional ARIMA model. This package provides Wavelet-ARIMA model for time series forecasting based on the algorithm by Aminghafari and Poggi (2012) and Paul and Anjoy (2018) <doi:10.1142/S0219691307002002> <doi:10.1007/s00704-017-2271-x>.

Last updated 3 years ago

1.48 score 1 dependents 8 scripts 179 downloads

TSLSTM - Long Short Term Memory (LSTM) Model for Time Series Forecasting

The LSTM (Long Short-Term Memory) model is a Recurrent Neural Network (RNN) based architecture that is widely used for time series forecasting. Min-Max transformation has been used for data preparation. Here, we have used one LSTM layer as a simple LSTM model and a Dense layer is used as the output layer. Then, compile the model using the loss function, optimizer and metrics. This package is based on Keras and TensorFlow modules and the algorithm of Paul and Garai (2021) <doi:10.1007/s00500-021-06087-4>.

Last updated 3 years ago

1.48 score 1 dependents 4 scripts 270 downloads

EEML - Ensemble Explainable Machine Learning Models

We introduced a novel ensemble-based explainable machine learning model using Model Confidence Set (MCS) and two stage Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) algorithm. The model combined the predictive capabilities of different machine-learning models and integrates the interpretability of explainability methods. To develop the proposed algorithm, a two-stage Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) framework was employed. The package has been developed using the algorithm of Paul et al. (2023) <doi:10.1007/s40009-023-01218-x> and Yeasin and Paul (2024) <doi:10.1007/s11227-023-05542-3>.

Last updated 7 months ago

1.30 score 259 downloads

VIRF - Computation of Volatility Impulse Response Function of Multivariate Time Series

Computation of volatility impulse response function for multivariate time series model using algorithm by Jin, Lin and Tamvakis (2012) <doi.org/10.1016/j.eneco.2012.03.003>.

Last updated 6 years ago

1.30 score 2 stars 159 downloads

UEI - Compute Uniform Error Index

Uniform Error Index is the weighted average of different error measures. Uniform Error Index utilizes output from different error function and gives more robust and stable error values. This package has been developed to compute Uniform Error Index from ten different loss function like Error Square, Square of Square Error, Quasi Likelihood Error, LogR-Square, Absolute Error, Absolute Square Error etc. The weights are determined using Principal Component Analysis (PCA) algorithm of Yeasin and Paul (2024) <doi:10.1007/s11227-023-05542-3>.

Last updated 7 months ago

1.00 score 2 scripts 215 downloads

PWEV - PSO Based Weighted Ensemble Algorithm for Volatility Modelling

Price volatility refers to the degree of variation in series over a certain period of time. This volatility is especially noticeable in agricultural commodities, adding uncertainty for farmers, traders, and others in the agricultural supply chain. Commonly and popularly used four volatility models viz, GARCH, Glosten Jagannatan Runkle-GARCH (GJR-GARCH) model, exponentially weighted moving average (EWMA) model and Multiplicative Error Model (MEM) are selected and implemented. PWAVE, weighted ensemble model based on particle swarm optimization (PSO) is proposed to combine the forecast obtained from all the candidate models. This package has been developed using algorithm of Paul et al. <doi:10.1007/s40009-023-01218-x> and Yeasin and Paul (2024) <doi:10.1007/s11227-023-05542-3>.

Last updated 10 months ago

1.00 score 166 downloads

WaveletGBM - Wavelet Based Gradient Boosting Method

Wavelet decomposition method is very useful for modelling noisy time series data. Wavelet decomposition using 'haar' algorithm has been implemented to developed hybrid Wavelet GBM (Gradient Boosting Method) model for time series forecasting using algorithm by Anjoy and Paul (2017) <DOI:10.1007/s00521-017-3289-9>.

Last updated 2 years ago

1.00 score 208 downloads

WaveletANN - Wavelet ANN Model

The wavelet and ANN technique have been combined to reduce the effect of data noise. This wavelet-ANN conjunction model is able to forecast time series data with better accuracy than the traditional time series model. This package fits hybrid Wavelet ANN model for time series forecasting using algorithm by Anjoy and Paul (2017) <DOI: 10.1007/s00521-017-3289-9>.

Last updated 2 years ago

1.00 score 2 scripts 252 downloads

WaveletRF - Wavelet-RF Hybrid Model for Time Series Forecasting

The Wavelet Decomposition followed by Random Forest Regression (RF) models have been applied for time series forecasting. The maximum overlap discrete wavelet transform (MODWT) algorithm was chosen as it works for any length of the series. The series is first divided into training and testing sets. In each of the wavelet decomposed series, the supervised machine learning approach namely random forest was employed to train the model. This package also provides accuracy metrics in the form of Root Mean Square Error (RMSE) and Mean Absolute Prediction Error (MAPE). This package is based on the algorithm of Ding et al. (2021) <DOI: 10.1007/s11356-020-12298-3>.

Last updated 3 years ago

1.00 score 188 downloads

WaveletSVR - Wavelet-SVR Hybrid Model for Time Series Forecasting

The main aim of this package is to combine the advantage of wavelet and support vector machine models for time series forecasting. This package also gives the accuracy measurements in terms of RMSE and MAPE. This package fits the hybrid Wavelet SVR model for time series forecasting The main aim of this package is to combine the advantage of wavelet and Support Vector Regression (SVR) models for time series forecasting. This package also gives the accuracy measurements in terms of Root Mean Square Error (RMSE) and Mean Absolute Prediction Error (MAPE). This package is based on the algorithm of Raimundo and Okamoto (2018) <DOI: 10.1109/INFOCT.2018.8356851>.

Last updated 3 years ago

1.00 score 153 downloads

WaveletGARCH - Fit the Wavelet-GARCH Model to Volatile Time Series Data

Fits the combination of Wavelet-GARCH model for time series forecasting using algorithm by Paul (2015) <doi:10.3233/MAS-150328>.

Last updated 5 years ago

1.00 score 1 stars 468 downloads