Neural network with fixed noise for index-tracking portfolio optimization

作者：

Highlights：

• Neural network with fixed noise to optimize the portfolio for tracking the index.

• Deep learning framework for full replication and partial replication.

• Experiments for tracking the S&P 500 index and Hang Seng Index.

• Critical parameters in index-tracking portfolio optimization using deep learning.

摘要

•Neural network with fixed noise to optimize the portfolio for tracking the index.•Deep learning framework for full replication and partial replication.•Experiments for tracking the S&P 500 index and Hang Seng Index.•Critical parameters in index-tracking portfolio optimization using deep learning.

论文关键词：Deep learning,Index-tracking portfolio optimization,Fixed noise

论文评审过程：Received 1 June 2020, Revised 3 April 2021, Accepted 25 May 2021, Available online 4 June 2021, Version of Record 11 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115298