Filters








240,508 Hits in 5.2 sec

Using the Mean Absolute Percentage Error for Regression Models [article]

Arnaud De Myttenaere, Bénédicte Le Grand
2015 arXiv   pre-print
We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models.  ...  We show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression.  ...  While the traditional measure is the quadratic error, in some applications, a more useful measure of the quality of the predictions made by a regression model is given by the mean absolute percentage error  ... 
arXiv:1506.04176v1 fatcat:jgo5sy2aebgobgi32ntn65xgky

Evaluating Hospital Case Cost Prediction Models Using Azure Machine Learning Studio [article]

Alexei Botchkarev
2018 arXiv   pre-print
The tool presents assessment results arranged by model accuracy in a single table using five performance metrics.  ...  The purpose of this experiment was to build an Azure Machine Learning Studio tool for rapid assessment of multiple types of regression models.  ...  Acknowledgement The views, opinions and conclusions expressed in this document are those of the author alone and do not necessarily represent the views of the author's current or former employers.  ... 
arXiv:1804.01825v2 fatcat:e6jw6kgtbvhijlg66ptpwa6qoe

A Comparison of Variable Selection by Tabu Search and Stepwise Regression with Multicollinearity Problem

Kannat Na Bangchang
2015 Journal of Statistical Science and Application  
In this study two objective functions used in the Tabu Search are mean square error (MSE) and the mean absolute error (MAE).  ...  However with multicollinearity problem the hit percentages of the Tabu Search using both objective functions are higher than the hit percentage of the stepwise regression method.  ...  , whether the MSE or the mean absolute error (MAE) is used as the objective function.  ... 
doi:10.17265/2328-224x/2015.12.002 fatcat:bdbrkzvxjvhrbp25cd4uvb6vfi

Predicting the performance of queues–A data analytic approach

Kum Khiong Yang, Tugba Cayirli, Joyce M.W. Low
2016 Computers & Operations Research  
used for modeling other complex systems.  ...  The proposed procedure of data analytics can be used to model other more complex systems.  ...  Error Number (%) 1 of Cases with Absolute Percentage Error > 20% Maximum Absolute Percentage Error for Worst Case Mean Absolute Error Maximum Absolute Error Mean Queue Length (  ... 
doi:10.1016/j.cor.2016.06.005 fatcat:zrnf4hrtyngvdenamklyd5pjdi

A New Proposal for the Shear Strength Prediction of Beams Longitudinally Reinforced with Fiber-Reinforced Polymer Bars

Czesław Bywalski, Michał Drzazga, Maciej Kaźmierowski, Mieczysław Kamiński
2020 Buildings  
Taking into account the extended base of destructive testing results, the estimation of the shear strength in accordance with the proposed model can be used as an accompanying (non-destructive) method  ...  A satisfactory level of model fit was obtained—the best among the available proposals.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/buildings10050086 fatcat:igrknqbzufdlhaefjx7leucc2i

Analysing Uncertainties in Offshore Wind Farm Power using Measure Correlate Predict Methodologies

Michael D. Mifsud, Tonio Sant, Robert N. Farrugia
2019 Zenodo  
The different MCP methods, that were implemented in Matlab®, are used to predict the absolute wind speed, while wind direction is predicted using the same regression methodology but, using the vector components  ...  The wake model introduces a more realistic value of the power output for the wind farm, as it includes the shadowing effects on the wind turbines and the [...]  ...  Mean Absolute Error, Mean Squared Error and Percentage Error in OVERALL Energy YIELD Mean Absolute Error, Mean Squared Error and Percentage Error in Overall Energy Yield.  ... 
doi:10.5281/zenodo.3359797 fatcat:raptvvzbvjdsfkztwrhiqcezma

The Combination Forecasting Model of Grain Production Based on Stepwise Regression Method and RBF Neural Network

Lihua Yang, Baolin Li
2015 Advance Journal of Food Science and Technology  
The performance of the models is measured using three types of error measurement, which are Mean Absolute Percentage Error (MAPE), Theil Inequality Coefficient (Theil IC) and Root Mean Squared Error (RMSE  ...  In order to improve the accuracy of grain production forecasting, this study proposed a new combination forecasting model, the model combined stepwise regression method with RBF neural network by assigning  ...  ACKNOWLEDGMENT The study has been supported by project of the Department of Education, Hubei Province China (NO. B20092306) and by project of Hubei University of Automotive Technology (No. 2012XQ02).  ... 
doi:10.19026/ajfst.7.2528 fatcat:lurb4zfzarepvo7mhiff3zpsgq

Modeling the Chemical Composition of Ferritic Stainless Steels with the Use of Artificial Neural Networks

Rafał Honysz
2021 Metals  
Artificial neural networks with radial basis functions (RBF), multilayer perceptron with one and two hidden layers (MLP) and generalized regression neural networks (GRNN) were used for modeling.  ...  The modeling results proved to be very promising and indicate that for some elements, this is possible with high accuracy.  ...  Conflicts of Interest: The author declares no conflict of interest.  ... 
doi:10.3390/met11050724 fatcat:rqcajop57feste7piz3zkydwdy

Forecasting N2O emission and nitrogen loss from swine manure composting based on BP neural network

Haotian Chen, Shaoze Sun, Baoli Zhang, W. Anggono
2019 MATEC Web of Conferences  
As for nitrogen loss, the mean error is 24.72 and the mean absolute percentage error is 11.06%.  ...  The analyses show that the mean error of N2O emission forecasting model is 1.17; the value of MAPE is 138.85%.  ...  Better than linear regression, which the mean squared error (MSE) is 19.28 and the mean absolute percentage error (MAPE) 50.49%.  ... 
doi:10.1051/matecconf/201927701010 fatcat:l5iotnhlazes3d2mkte3hwjzvq

Investigation of One Day Ahead Load Forecasting for Iraqi Power System

Mohammed Abdulla, Mohanad Azeez, Firas M.
2017 International Journal of Computer Applications  
The ANN gives a very small mean absolute percentage error (MAPE) compared with MLR but it takes a longer time for training process.  ...  In this paper the short term load forecasting (STLF) using feed forward Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) techniques for Iraqi power system (IPS) is presented.  ...  The performance accuracy of the two techniques is measured using mean absolute percentage error (MAPE).  ... 
doi:10.5120/ijca2017913450 fatcat:cp5umdnegzg7hhmd5cs6vblc3y

The Evaluation of Forecasting Methods at an Institutional Foodservice Dining Facility

Kisang Ryu, Alfonso Sanchez
2003 Journal of Hospitality Financial Management  
The accuracy of the forecasting methods was measured using mean absolute deviation, mean squared error, mean percentage error, mean absolute percentage error, root mean squared error, and Theil's U-statistic  ...  The purpose of this study was to identify the most appropriate method of forecasting meal counts for an institutional food service facility.  ...  = Holt's method; WES = Winter's method; LR = linear regression; MR = multiple regression; MAD = mean absolute deviation; MSE = mean squared error; MPE = mean percentage error; MAPE = mean absolute percentage  ... 
doi:10.1080/10913211.2003.10653769 fatcat:6qitoz5thrdcdg5m6w5m3k6scy

COMPARISON OF SOME STATISTICAL FORECASTING TECHNIQUES WITH GMDH PREDICTOR: A CASE STUDY

Syed Misbah Uddin, Aminur Rahman, Emtiaz Uddin Ansari
2018 Journal of Mechanical Engineering  
The mean absolute deviation (MAD, mean absolute percentage error (MAPE) and mean square error (MSE) were also calculated for comparing the forecasting accuracy.  ...  The comparison of modelling results shows that the GMDH model perform better than other statistical models based on terms of mean absolute deviation (MAD), mean absolute percentage error (MAPE) and mean  ...  The mean absolute deviation (MAD), mean absolute percentage error (MAPE) and mean square error (MSE) were also calculated to assess forecasting performance of different models.  ... 
doi:10.3329/jme.v47i1.35354 fatcat:qs4f2wbdbrbtxpdeup3qdjuw7m

Techniques for predicting total phosphorus in urban stormwater runoff at unmonitored catchments

D. May, M. Sivakumar
2004 ANZIAM Journal  
Regression models calibrated using event mean concentration (emc) as the dependent variable were more accurate than those using event load.  ...  Regression models developed on a regional subset of data were more accurate than the models developed on the entire data set.  ...  Acknowledgments: The authors express their gratitude to Pam Davy for her assistance during the course of the research.  ... 
doi:10.21914/anziamj.v45i0.889 fatcat:atmxraieuve4xbbmvafb65j7oy

Consumers' willingness to pay for green electricity: A meta-analysis of the literature

Swantje Sundt, Katrin Rehdanz
2015 Energy Economics  
When assessing the predictive power of our results for out-of-sample value transfers we find median errors of approximately 30%, depending on model specification.  ...  Based on results of a meta-regression our results indicate e.g. that hydropower is the least preferred technology.  ...  The mean absolute error is 1.02 US-Cents per kilowatt-hour.If we exclude the outliers identified above, mean absolute error decreases (0.82 US-Cents).Median absolute percentage error (22.16%) and MAPE  ... 
doi:10.1016/j.eneco.2015.06.005 fatcat:cog4k2kpmze3tnxn573nt6gcra

Stock market volatility and the forecasting performance of stock index futures

Janchung Wang
2009 Journal of Forecasting  
The forecasting techniques applied were random walk, moving average, simple regression and historical mean. The error in forecasting was measured by symmetric and asymmetric error statistics.  ...  The most suitable volatility forecasting technique for Bursa Malaysia Plantation Index was simple regression technique.  ...  The mean absolute error, root mean squared error, and mean absolute percentage error were used to evaluate the performance of the competing models.  ... 
doi:10.1002/for.1101 fatcat:zvipym3pgbbp3mcd7bm5dsusmm
« Previous Showing results 1 — 15 out of 240,508 results