Products & Solutions / By Solution / Forecaster XL / Feature Set

• Regression, classification types of forecasting
• Time-series forecasting
• Exceptional ease of use
• Constructive neural network algorithms
• Informative graphs and detailed reports
• Online help system
• Free technical support
• Multi-language interface
• Sample financial, marketing, real estate and scientific problems included

• Number of inputs and records are limited only by Excel limitations
• Automatic data analysis and pre-processing
• Automatic categorical values encoding
• Automatic numeric values scaling
• Missing values handling for numeric values (removal and 4 substitution options)
• Missing values handling for categorical values (removal and 3 substitution options)
• Outliers handling (customizable outlier coefficient)
• Manual min/max values specification to anticipate bigger values in data for forecasting
• Automatic random and sequential dataset partition onto training and test sets
• Detailed Data Analysis and Preprocessing Report

• Fully automated neural network design - a special state-of-the-art constructive algorithm automatically creates and trains the most suitable neural network to solve your problem.
• Neural networks for time-series forecasting
• Unique "Next Target" mode: combination of regression and time-series forecasting
• Automatic generation of versatile stopping condition to stop network training
• Generalization loss control (10 preset levels)
• Retain and restore best network
• Manual network retrain
• Retrain network to get better results

For experienced users
• Manual stopping conditions (target error level, error improvement, correct classification rate, number of iterations)
• Real-time control on training parameters (MSE, MAE, CCR, # of iterations).
• Training Error Graph (network error by iteration)
• Training Error Table (network error and error improvement by iteration)
• Cost/Loss matrix

• Actual vs Forecasted Graph
• Actual vs Forecasted Scatter Plot
• Input Importance Chart
• Error deviation graph
• Actual vs Forecasted Table with absolute and relative errors
• Confusion matrix
• Error distribution table
• R-squared and correlation calculation for a network
• Tolerance levels to quickly estimate overall forecasting quality
• Single-point forecasting and bulk forecasting
• Quick forecasting with already trained network

• two convenient methods of data selection: by range and by column
• complete color customization for reports and graphs
• neural network autosave
• load/save neural network from/to Excel worksheet/workbook