Investment factor timing: Harvesting the low-risk anomaly using artificial neural networks

作者：

Highlights：

• Long Short Term Memory Neural Networks are a good fit for factor risk forecasting.

• Downside deviation most effective to select factors in context of low-risk anomaly.

• Model is able to differentiate between positive and negative performing factors.

• Successful risk-based factor timing strategy, also beating GARCH-based strategy.

摘要

•Long Short Term Memory Neural Networks are a good fit for factor risk forecasting.•Downside deviation most effective to select factors in context of low-risk anomaly.•Model is able to differentiate between positive and negative performing factors.•Successful risk-based factor timing strategy, also beating GARCH-based strategy.

论文关键词：Factor investing,Low-risk anomaly,Neural networks,Long-short term memory

论文评审过程：Received 27 April 2020, Revised 6 September 2021, Accepted 12 October 2021, Available online 24 October 2021, Version of Record 8 November 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116093