The strategy uses news-driven returns to sort ETFs into quintiles daily, taking long-short positions on top and bottom quintiles, holding until market close, leveraging sector-specific news data.
ASSET CLASS: ETFs | REGION: United States | FREQUENCY:
Intraday | MARKET: equities | KEYWORD: News
I. STRATEGY IN A NUTSHELL
Daily trading strategy using 226 sector ETFs and 4,300 U.S. stocks linked to news from RavenPack. ETFs are sorted into quintiles based on value-weighted news-driven returns at 10 a.m.; long the top quintile, short the bottom, holding positions until market close.
II. ECONOMIC RATIONALE
Exploits short-term underreaction to news: stocks in news-driven ETFs show momentum, while others revert. Aggregating at the ETF level predicts sector-level returns. Practical concerns include signal decay, trading delays, and transaction costs, which may reduce realized alpha.
III. SOURCE PAPER
Predicting High-Frequency Industry Returns: Machine Learners Meet News Watchers [Click to Open PDF]
Hao Jiang, Michigan State University – Eli Broad College of Business; Sophia Zhengzi Li, Rutgers, The State University of New Jersey – Rutgers Business School at Newark & New Brunswick; Peixuan Yuan, Hong Kong Baptist University
<Abstract>
This paper shows a strong link between the granular information contained in individual stock prices and sectoral movements. We find that a predictor aggregating the price movements of a broad cross section of individual stocks predicts sector ETF returns at intraday and lower frequencies. When we further incorporate the information from structural models, the resulting information signals have even stronger return predictability. A trading strategy that exploits the return predictability is profitable after trading costs. These results support theories of granular and network origins of aggregate shocks.
IV. BACKTEST PERFORMANCE
| Annualised Return | 21.12% |
| Volatility | 9.82% |
| Beta | N/A |
| Sharpe Ratio | 2.15 |
| Sortino Ratio | N/A |
| Maximum Drawdown | N/A |
| Win Rate | N/A |
