Package: RWInfoLSTM
Type: Package
Title: Random Walk-Informed LSTM for Time Series Forecasting
Version: 0.1.0
Authors@R: c(
    person(given = "Md", family = "Yeasin", role = "aut"),
    person(given = "Ranjit Kumar", family = "Paul",
           email = "ranjitstat@gmail.com", role = c("aut", "cre")),
    person(given = "Pushkar", family = "Bora", role = "aut")
  )
Maintainer: Ranjit Kumar Paul <ranjitstat@gmail.com>
Description: Implements a Random Walk (RW)-informed Long Short-Term Memory
    (LSTM) network for univariate time series forecasting. The LSTM is
    trained on the full series with a composite loss that blends the usual
    mean squared error (MSE) between predictions and observations with the
    MSE between predictions and the fitted Random Walk, weighted by a
    parameter lambda (0 gives a standard LSTM, 1 gives a fully RW-guided
    LSTM). The Random Walk, either simple or with drift, is selected
    automatically by its in-sample root mean squared error (RMSE), and the
    lambda value with the lowest training RMSE is retained. The LSTM
    hyperparameters can be supplied manually or tuned by grid search, and
    functions for out-of-sample forecasting, accuracy measures and plots
    are provided. The methodology is motivated by hybrid forecasting
    framework proposed by Yeasin and Paul (2024)
    <doi:10.1007/s11227-023-05542-3>.
License: MIT + file LICENSE
Encoding: UTF-8
Imports: torch (>= 0.11.0), coro, ggplot2 (>= 3.4.0), cli (>= 3.6.0),
        stats, utils
Suggests: testthat (>= 3.0.0)
Config/testthat/edition: 3
Config/roxygen2/version: 8.1.1
NeedsCompilation: no
Packaged: 2026-10-19 16:24:45 UTC; borap
Author: Md Yeasin [aut],
  Ranjit Kumar Paul [aut, cre],
  Pushkar Bora [aut]
Repository: CRAN
Date/Publication: 2026-10-29 12:00:02 UTC
