![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_open_medium.gif)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_restricted_medium.gif)
An Ensemble Model for Pattern Prediction Problems
Subscribe/Renew Journal
Stock markets are non-linear and chaotic in nature.Though fundamental and technical analysis are used for forecasting the future values of the share prices, as the data involved is voluminous, it is difficult for correct predictions. Neural networks are extensively used by researchers for solving pattern recognition problems. In literature, single level ensemble models are seen. Hence, a two level neural network based ensemble model, “Pattern Prediction Ensemble Model (PAPEM)” is proposed. This model is experimentally found to increase the prediction accuracy of non-linear time series systems. The PAPEM model can be employed in non-linear time series prediction problems like Stock Predictions, Commodity Trading, Forex Trading, Mackey glass, Sunspot, North Atlantic Oscillation Predictions and Electricity Demand Forecasting. Experiments have proved that the performance of the PAPEM model is better than the performance of the individual neural network and single level ensemble models.
Keywords
Cascade Forward Neural Network, Feed Forward Back Propagation Neural Network, Ensemble, Time Series Prediction.
User
Subscription
Login to verify subscription
Font Size
Information
![](https://i-scholar.in/public/site/images/abstractview.png)
Abstract Views: 231
![](https://i-scholar.in/public/site/images/pdfview.png)
PDF Views: 4