ModAugNet: A new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module
作者：
Highlights：
• Proposed a new modularized forecasting framework (ModAugNet) for stock market.
• ModAugNet has two LSTM modules: overfitting Prevention Module and Prediction Module.
• Found that Prevention Module helps to prevent network from overfitting when training.
• Verified that ModAugNet significantly outperformed a model without Prevention Module.
• Showed that test performance solely depends on test input of Prediction Module.
摘要
•Proposed a new modularized forecasting framework (ModAugNet) for stock market.•ModAugNet has two LSTM modules: overfitting Prevention Module and Prediction Module.•Found that Prevention Module helps to prevent network from overfitting when training.•Verified that ModAugNet significantly outperformed a model without Prevention Module.•Showed that test performance solely depends on test input of Prediction Module.
论文关键词：Long short-term memory,Data augmentation,Overfitting,Deep learning,Stock market index
论文评审过程：Received 11 March 2018, Revised 6 July 2018, Accepted 7 July 2018, Available online 9 July 2018, Version of Record 20 July 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.07.019
