• Corpus ID: 2802742

Measuring forecast accuracy

@inproceedings{Hyndman2014MeasuringFA,
  title={Measuring forecast accuracy},
  author={Rob J Hyndman},
  year={2014}
}
It is important to evaluate forecast accuracy using genuine forecasts. That is, it is invalid to look at how well a model fits the historical data; the accuracy of forecasts can only be determined by considering how well a model performs on new data that were not used when estimating the model. When choosing models, it is common to use a portion of the available data for testing, and use the rest of the data for estimating (or “training”) the model. Then the testing data can be used to measure… 

Figures and Tables from this paper

Hierarchical forecasting of engineering demand at KLM Engineering & Maintenance

A framework that applies multiple models and leverages the benefits of forecast combination and reconciliation to enable aligned decisions for capacity on both tactical and operational levels is proposed and testing the proposed framework indicate that significant improvements are possible.

Forecasting Electricity Generation Capacity in Malaysia : An Auto Regressive Integrated Moving Average Approach

It is imperative for Malaysia to have a clear understanding of the future performance of its power sector with emphasis on the total installed capacity variable as this is integral to support the

ANALYSIS OF UNEVENLY SPACED TIME SERIES DATA IN HIGHLY DISTRIBUTED AND UNRELIABLE NETWORKS

By selecting a forecasting method that has the best accuracy (the smallest error) for adequate and recognized type of time series, an automated recursive predicting function is presented.

Stock Market Volatility Modeling and Forecasting with a Special Reference to BSE Sensex

This study is intended to investigate the volatility patterns in Bombay Stock Exchange Limited Sensitivity Index (BSE Sensex) based on time series data collected for 10 years period of time. To reach

Bayesian enhanced ensemble approach (BEEA) for time series forecasting

Relative advantages and limitations of the ensemble approach in contrast with some reported in the literature are illustrated to highlight the effectiveness of the Bayesian enhanced ensemble approach (BEEA) through different forecasting horizons.

Comparison of Classical and Nonlinear Models for Short-Term Electricity Price Prediction

Two contrasting machine learning approaches for predicting electricity prices, regression decision trees and recurrent neural networks, are tested and found to achieve high performance, suggesting that regression trees should be more carefully considered for electricity price forecasting.

A Novel Method for Sea Surface Temperature Prediction Based on Deep Learning

A novel model of SST prediction integrated Deep Gated Recurrent Unit and Convolutional Neural Network (DGCnetwork) is proposed, which has a compact structure and focuses on learning deep long-term dependencies in SST time series.

Urban Electric Load Forecasting with Mobile Phone Location Data

This paper harnesses society-wide mobile phone data to map the time-varying population distribution in the Trentino region, Italy, and to use these insights for a novel electrical load forecasting method, demonstrating that the integration of aggregated mobile phoneData yields compelling forecast models.

References

SHOWING 1-4 OF 4 REFERENCES

Another look at measures of forecast accuracy

Automatic Time Series Forecasting: The forecast Package for R

Two automatic forecasting algorithms that have been implemented in the forecast package for R, based on innovations state space models that underly exponential smoothing methods, are described.

Forecasting: principles and practice. OTexts. http://otexts.com/fpp

  • 2012

Forecasting: principles and practice. OTexts

  • Forecasting: principles and practice. OTexts
  • 2012