Robo-advisor using genetic algorithm and BERT sentiments from tweets for hybrid portfolio optimisation

作者：

Highlights：

• We proposed two robo-advisors capturing market conditions through Twitter sentiments.

• Google’s BERT model was used to convert tweets to sentiments.

• Genetic algorithm was used to optimise the models for different objectives.

• The proposed models achieved superior portfolio performance.

摘要

•We proposed two robo-advisors capturing market conditions through Twitter sentiments.•Google’s BERT model was used to convert tweets to sentiments.•Genetic algorithm was used to optimise the models for different objectives.•The proposed models achieved superior portfolio performance.

论文关键词：BERT,Portfolio optimisation,Genetic algorithm,Social media sentiment analysis,Twitter

论文评审过程：Received 28 January 2021, Revised 23 March 2021, Accepted 15 April 2021, Available online 22 April 2021, Version of Record 4 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115060