Ensembling Deep Learning and Evolutionary Methods for ETF Investing

Summary

The paper proposes a systematic investment approach intended to build wealth over a longer horizon through a sequence of short-term ETF purchase decisions. It combines evolutionary algorithms with a deep learning model to improve the timing of contributions compared with conventional daily systematic investment. The aim is to adapt purchase decisions over time rather than invest the same way on every scheduled day.

The authors report approximately one percent higher returns than traditional daily systematic investment for a given ETF. They say the evidence comes from live algorithmic trading decisions executed through a retail brokerage platform, rather than solely from a simulated backtest. The brief description does not specify the ETF, evaluation period, risk measures, costs, or whether the comparison generalizes to other funds and market conditions. The reported difference therefore provides a case study, not a broad guarantee that the ensemble will improve long-term investment outcomes.

Key ideas

• The method combines evolutionary algorithms and deep learning to guide ETF purchase decisions.
• It targets long-term wealth accumulation through a series of short-term investment choices.
• The comparison is with conventional daily systematic investment in a given ETF.
• The authors report about one percent higher returns using live algorithmic decisions, with limited details on generalizability.

Tags

# Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies


# Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies









Machine learning driven trading strategies have garnered a lot of interest over the past few years. There is, however, limited consensus on the ideal approach for the development of such trading strategies. Further, most literature has focused on trading strategies for short-term trading, with little or no focus on strategies that attempt to build long-term wealth. Our paper proposes a new approach for developing long-term investment strategies using an ensemble of evolutionary algorithms and a deep learning model by taking a series of short-term purchase decisions. Our methodology focuses on building long-term wealth by improving systematic investment planning (SIP) decisions on Exchange Traded Funds (ETF) over a period of time. We provide empirical evidence of superior performance (around 1% higher returns) using our ensemble approach as compared to the traditional daily systematic investment practice on a given ETF. Our results are based on live trading decisions made by our algorithm and executed on the Robinhood trading platform.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.