Scaling High-Frequency S&P Returns for Model-Based Intraday Trading

Summary

The paper uses scaling properties of aggregated S&P 500 high-frequency returns to construct a martingale stochastic model. The model is designed to reproduce conditional expectations for the morning session, then extended to cover afternoon trading. Forecasts from the model generate intraday trend-following signals; the signals come from the model rather than chart patterns. The proposed strategy seeks to exploit linear correlations found in the S&P data but absent from the model.

In-sample and out-of-sample tests are reported to show better performance than a benchmark based on an asymmetric GARCH process, along with small arbitrage opportunities. The authors state that profits would disappear without the linear correlations and discuss possible use in hedging volatility risk for S&P-linked products. The supplied description does not give test dates, implementation assumptions, transaction costs, or numerical performance details, limiting assessment of robustness and tradability. The reported edge is tied to the specified data properties and model comparison.

Key ideas

• Scaling in aggregated high-frequency returns is used to build a martingale model for conditional expectations.
• The model is extended from the morning session to afternoon trading.
• Model forecasts generate intraday trend-following signals without chart-based criteria.
• The strategy’s reported profits depend on linear correlations present in the S&P data.
• Tests report an advantage over an asymmetric GARCH benchmark, but implementation details are not provided.

Tags

# Ensemble properties of high frequency data and intraday trading rules


# Ensemble properties of high frequency data and intraday trading rules









Regarding the intraday sequence of high frequency returns of the S&P index as daily realizations of a given stochastic process, we first demonstrate that the scaling properties of the aggregated return distribution can be employed to define a martingale stochastic model which consistently replicates conditioned expectations of the S&P 500 high frequency data in the morning of each trading day. Then, a more general formulation of the above scaling properties allows to extend the model to the afternoon trading session. We finally outline an application in which conditioned forecasting is used to implement a trend-following trading strategy capable of exploiting linear correlations present in the S&P dataset and absent in the model. Trading signals are model-based and not derived from chartist criteria. In-sample and out-of-sample tests indicate that the model-based trading strategy performs better than a benchmark one established on an asymmetric GARCH process, and show the existence of small arbitrage opportunities. We remark that in the absence of linear correlations the trading profit would vanish and discuss why the trading strategy is potentially interesting to hedge volatility risk for S&P index-based products.

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.