Forecasting of stock return prices with sparse representation of financial time series over redundant dictionaries
作者：
Highlights：
• A new predictive model for time series within the financial sector is presented.
• The method is based on learned redundant dictionaries for sparse representation of financial time series.
• The overall return gain generated by the predictive model exceeds the gain generated by the market.
• Untrained dictionaries outperform dictionaries trained with the KSV-D method.
• Untrained dictionaries require a reduced number of atoms to achieve successful results.
摘要
•A new predictive model for time series within the financial sector is presented.•The method is based on learned redundant dictionaries for sparse representation of financial time series.•The overall return gain generated by the predictive model exceeds the gain generated by the market.•Untrained dictionaries outperform dictionaries trained with the KSV-D method.•Untrained dictionaries require a reduced number of atoms to achieve successful results.
论文关键词：Financial time series,Artificial financial predictors,Sparse representation,Learned over-redundant dictionaries,Temporal feature extraction,Time-domain pattern recognition
论文评审过程：Received 4 October 2015, Revised 4 March 2016, Accepted 5 March 2016, Available online 19 March 2016, Version of Record 5 April 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.03.021
