A covered call ETF is an exchange-traded fund that employs a covered call strategy to generate income while maintaining exposure to the underlying assets. This strategy involves holding a portfolio of stocks and selling (or “writing”) call options on those stocks to collect option premiums. Covered call ETFs are particularly popular among income-seeking investors, as the premiums collected provide an additional source of returns, potentially enhancing yield.
The growing popularity of covered call ETFs not only attracts investor capital but also draws attention from academics. Reference [1] studied predictive models for forecasting the performance of covered call ETFs. Specifically, the authors utilized traditional time series methods, advanced ML techniques, and Deep Learning models. They pointed out,
This study builds on the existing financial literature to comprehensively assess forecasting models for covered call ETFs, offering a comparative analysis of time series, machine learning, and deep learning techniques.
The findings from the study indicate that, for the traditional time series models, the ARIMA model outperforms the HAR model for tickers QYLD and JEPQ, while the HAR model outperforms the ARIMA model with tickers XYLD, JEPI and RYLD. For the ML models, The RF model consistently outperforms the SVR model for all tickers except for JEPQ, where the SVR slightly outperforms the RF model. Similarly, the RF model consistently shows a better fit compared to the SVR model. For the DL models, The RNN model consistently outperforms the CNN model for all the covered call ETFs; however, the CNN model displays a superior fit. Similarly, the RNN model consistently outperforms all the time–series and ML models in the study, making it the most effective at predicting the prices of covered call ETFs.
In short, the results indicate that Deep Learning models are effective at identifying the nonlinear patterns and temporal dependencies in the price movements of covered call ETFs, outperforming both traditional time series and ML techniques.
We find this result interesting, as the returns of these covered call ETFs have the volatility risk premium embedded in them, yet these techniques are still capable of predicting these more sophisticated instruments.
We are closely following research that explores how covered call ETFs are changing market dynamics.
Let us know what you think in the comments below or in the discussion forum.
References
[1] Chigozie Andy Ngwaba, Forecasting Covered Call Exchange-Traded Funds (ETFs) Using Time Series, Machine Learning, and Deep Learning Models, J. Risk Financial Manag. 2025, 18, 120
Further questions
What's your question? Ask it in the discussion forum
Have an answer to the questions below? Post it here or in the forum
