Predicting Futures Basis with ETF Premiums and Discounts

Summary

This report summary describes a composite signal for forecasting changes in futures basis using high-frequency ETF premiums and discounts. It separates ETF observations into intraday comparisons, such as the close versus the open or the day's average, and day-to-day comparisons against the prior close or average. The proposed connection is that ETF pricing deviations contain information about the relationship between futures and spot markets.

The method also uses two basis behaviors: mean reversion, inferred from comparing the current basis with the previous day's, and convergence toward zero as a futures contract approaches expiry. These components are combined into an overall forecast. The summary reports backtest signal frequencies and win rates for three index basis series over a stated historical period, but offers no details on transaction costs, execution, sample construction, or out-of-sample performance. The findings therefore describe a historical signal test and do not establish that the forecasts remain effective in other periods or after trading frictions.

Key ideas

• ETF premium and discount measures are divided into intraday and day-to-day signals.
• The report uses the previous day's basis to infer possible mean reversion in the next day's basis change.
• A contract nearing expiry is expected to have basis converge toward zero under no-arbitrage pricing.
• The individual components are combined into a composite basis forecast.
• Reported results are historical backtests, and the summary does not specify costs or out-of-sample validation.

Tags

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