One popular alternative to using either A or F as the denominator is to take an average of the two: (A+F)/2. Calculated over multiple forecast periods, this measure is most commonly called the symmetric MAPE (sMAPE) and has been used in recent forecasting competitions to compare the accuracy of forecasts from different methods. See, for example, www. neural-forecasting-competition.com/index.htm...

The objective of this paper is to develop a novel wind speed forecasting technique, which produces more accurate prediction. The Wavelet Transform (WT) along with the Auto Regressive Moving Average (ARMA) is chosen to form a hybrid whose combination is expected to give minimum Mean Absolute Prediction Error (MAPE). A simulation study has been conducted by comparing the forecasting results using...

Fuzzy time series model has been developed to either improve forecasting accuracy or reduce computation time, whereas a residul analysis in order to improve its forecasting performance is still lack of consideration. In this paper, we propose a novel Fourier method to revise the analysis of residual terms, and then we illustrate it to forecast the Japanese tourists visiting in Taiwan per year. ...

This paper performs an experiment to forecast stock market movement in India using Artificial Neural Network (ANN) and Genetic Algorithm (GA). This model is named Genetically optimized Neural Network (GNN). We have tested this newly created model against traditional ARCH/GARCH models using hypothesis testing (z-test).We have used different error metrics like Average Absolute Error (AAE), Mean A...

In this paper we have generated computer images from a C++ computer program and have then developed an artificial neural network model based on MAPE type of error from two samples of points obtained from the generated images using predictive modeling software. The obtained model was imported to Matlab Signal Processing Tool (SPTool) via Matlab workspace. We have applied a band pass filter to th...

The financial performance of a company can be predicted using various methods, one which is linear regression and exponential smoothing. This study aims to predict the PT Astra International Tbk smoothing as well combining both methods obtain more accurate predictions. Financial data from 2012-2021 was used in this study. results prediction with show that current ratio has lowest MAPE, while sh...

In this paper an attempt is made to develop hybrid models using Artificial Neural Network (ANN) and Autoregressive Integrated Moving Average (ARIMA) for predicting the future exchange rate for US dollar. Simulation results of hybrid models were compared with results of ANN based models and ARIMA based models. Results show that the model ANN – ARIMA ANN gives a better performance than the other ...

Self-healing and self-configuration are highly desirable properties in software systems so that components can dynamically adapt to changing environments and recover from failure with minimal human intervention. This paper discusses a model-based approach for self-healing and self-configuration using recovery connectors. A recovery connector extends connectors in component-based software archit...

The focus of this paper is to construct daily time series exchange rate forecast models of Samoan Tala/USD and Tala/AUD during the year 2008 to 2012 with neural network The performance of the models was measured by using varies error functions such as Root Square mean error (RSME), Mean absolute error (MAE), and Mean absolute percentage error (MAPE). Our empirical findings suggest that AR (1) m...

To investigate the applicability of ARIMA models in wholesale vegetable market models are built taking sales data of one perishable vegetable from Ahmedabad wholesales market in India. It is found that these models can be applied to forecast the demand with Mean Absolute Percentage Error (MAPE) in the range of 30%. This error is acceptable in fresh produce market where the demand and prices are...