The nnfor (development version here) package for R facilitates time series forecasting with Multilayer Perceptrons (MLP) and Extreme Learning Machines (ELM). Currently (version 0.9.6) it does not support deep learning, though the plan is to extend this to this direction in the near future. Currently, it relies on the neuralnet package for R, which provides… Read More: Tutorial for the nnfor R package »
The tsutils package for R includes functions that help with time series exploration and forecasting, that were previously included in the TStools package that is only available on github. The name change was necessary as there is another package on CRAN with the same name. The objective of TStools is to provide a development and… Read More: R package: tsutils »
A feature that was missing in the nnfor package was the ability to reuse and retrain mlp and elm model fits. This is now possible with the new arguments model and retrain. As an example, let us use the AirPassengers time series, with three different sample sizes and re-use and re-train the same model in… Read More: Update for nnfor: reuse and retrain models »
I have been asked a few time to provide an example how to use MAPAx, from the MAPA package for R, so I prepared this blog post. I admit the documentation could be better, so I put together this example from a retailing case – the original setting MAPAx was developed for (see paper here).… Read More: MAPAx example for R »
I have put up a github repository for the nnfor package for R: https://github.com/trnnick/nnfor I will be putting updates and fixes there, before they are pushed on CRAN. You can also report there bugs. You can install the current github version with: Related PostsCan neural networks predict trended time series? MAPA package for R on… Read More: nnfor on github »
My new R package nnfor is available on CRAN. This collects the various neural network functions that appeared in TStools. See this post for demo of these functions. In summary the package includes: Automatic, semi-automatic or fully manual specification of MLP neural networks for time series modelling, that helps in specifying inputs with lags of the… Read More: New R package nnfor: time series forecasting with neural networks »
I recently got my hands on a physical copy of my new book: Principles of Business Forecasting (2nd edition). Ord, K., Fildes, R. and Kourentzes, N., 2017. Principles of business forecasting. 2nd ed. Wessex Press Publishing Co. I was invited by Keith Ord and Robert Fildes to join them in writing the much-revised 2nd edition… Read More: Principles of Business Forecasting 2e »
Last February Facebook open sourced its Prophet forecasting tool. Since, it had appeared in quite a few discussions online. A good thing about Prophet is that it one can use it very easily through R (and Python). This gave me the opportunity to benchmark it against some more standard – and not! – forecasting models… Read More: Benchmarking Facebook’s Prophet »
You can find the material from yesterday’s workshop at the International Symposium on Forecasting, 2017 here. The workshop notes assume some knowledge of what the various forecasting methods do, and the main focus is on showing which functions to use and how, so as to perform a wide variety of forecasting tasks: Time series exploration… Read More: Material for `Forecasting with R: A practical workshop’ at ISF2017 »
I have been looking for a package to do time series modelling in R with neural networks for quite some time with limited success. The only implementation I am aware of that takes care of autoregressive lags in a user-friendly way is the nnetar function in the forecast package, written by Rob Hyndman. In my… Read More: Forecasting time series with neural networks in R »