CRAN/E | OptiSembleForecasting

OptiSembleForecasting

Optimization Based Ensemble Forecasting Using MCS Algorithm

Installation

About

The real-life data is complex in nature. No single model can capture all aspect of complex time series data. In this package, 14 models, namely Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Bidirectional LSTM, Deep LSTM, Artificial Neural Network (ANN), Support Vector Regression (SVR), Random Forest (RF), k-Nearest Neighbour (KNN), XGBoost (XGB), Autoregressive Integrated Moving Average (ARIMA), Error-Trend-Seasonality (ETS) and TBATS models, have been implemented and their accuracy have been checked. An PCA based error index has been proposed to select a group of best models using MCS algorithms. After selecting the models, the forecasts from these models have been ensembled using optimization techniques. This package allows to implement 20 optimization techniques, namely, Artificial Bee Colony (ABC), Ant Lion Optimizer (ALO), Bat Algorithm (BA), Black Hole Optimization Algorithm (BHO), Clonal Selection Algorithm (CLONALG), Cuckoo Search (CS), Cat Swarm Optimization (CSO), Dragonfly Algorithm (DA), Differential Evolution (DE), Firefly Algorithm (FFA), Genetic Algorithm (GA), Gravitational Based Search Algorithm (GBS), Grasshopper Optimisation Algorithm (GOA), Grey Wolf Optimizer (GWO), Harmony Search Algorithm (HS), Krill-Herd Algorithm (KH), Moth Flame Optimizer (MFO), Particle Swarm Optimization (PSO), Sine Cosine Algorithm (SCA), Shuffled Frog Leaping (SFL) and Whale Optimization Algorithm (WOA). This package has been developed using concept of Wang et al. (2022) doi:10.1016/j.apm.2022.09.004, Qu et al. (2022) doi:10.1016/j.eswa.2022.118746 and Kriz (2019) doi:10.1007/978-3-030-18195-6_21 .

Key Metrics

Version 0.1.0
Published 2022-09-20 556 days ago
Needs compilation? no
License GPL-3
CRAN checks OptiSembleForecasting results

Downloads

Yesterday 6 0%
Last 7 days 35 -31%
Last 30 days 176 -10%
Last 90 days 710 +33%
Last 365 days 2.333 +107%

Maintainer

Maintainer

Dr. Md Yeasin

yeasin.iasri@gmail.com

Authors

Dr. Md Yeasin

aut / cre

Dr. Ranjit Kumar Paul

aut

Material

Reference manual
Package source

macOS

r-release

arm64

r-oldrel

arm64

r-release

x86_64

r-oldrel

x86_64

Windows

r-develnot available

x86_64

r-releasenot available

x86_64

r-oldrelnot available

x86_64

Imports

stats
keras
tsutils
readxl
tibble
tensorflow
Metrics
forecast
dplyr
neuralnet
MCS
caretForecast
kknn
metaheuristicOpt
FactoMineR
factoextra
utils