Title: | Time Series Forecasting using SVM Model |
---|---|
Description: | Implementation and forecasting univariate time series data using the Support Vector Machine model. Support Vector Machine is one of the prominent machine learning approach for non-linear time series forecasting. For method details see Kim, K. (2003) <doi:10.1016/S0925-2312(03)00372-2>. |
Authors: | Mrinmoy Ray [aut, cre], Samir Barman [aut, ctb], Kanchan Sinha [aut, ctb], K. N. Singh [aut, ctb] |
Maintainer: | Mrinmoy Ray <[email protected]> |
License: | GPL-3 |
Version: | 0.1.0 |
Built: | 2024-11-20 06:47:04 UTC |
Source: | CRAN |
The ARSVM function fit Auto-Regressive Support Vector Machine for univariate time series data.
ARSVM(data,h)
ARSVM(data,h)
data |
Input univariate time series (ts) data. |
h |
The forecast horizon. |
This package allows you to fit the Auto-Regressive Support Vector Machine for univariate time series.
Optimum lag |
Optimum lag of the considered data |
Model Summary |
Summary of the fitted SVM |
Weights |
weights of the fitted SVM |
Constant |
Constant of the fitted SVM |
MAPE |
Mean Absolute Percentage Error (MAPE) of the SVM |
RMSE |
Root Mean Square Error (RMSE) of fitted SVM |
fitted |
Fitted values of SVM |
forecasted.values |
h step ahead forecasted values employing SVM |
Mrinmoy Ray,Samir Barman, Kanchan Sinha, K. N. Singh
Kim, K.(2003). Financial time series forecasting using support vector machines, 55(1-2), 307-319.
SVM
data=lynx ARSVM(data,5)
data=lynx ARSVM(data,5)