Backtest: Buy ET at the close when its daily news-sentiment score is in the bottom quin...
Selling into bad headlines only pays if the headlines are wrong about the cash flow. That is the premise tested here: buy ET at the close when its news-sentiment score lands in the bottom quintile of the prior 20 sessions, but only while Brent holds above its 20-day average — a filter meant to separate a sentiment flush from a real break in the midstream story. Exit on a close above the 5-day average, or after five sessions at most.
Across 94 closed trades the win rate came in at 59.1%, and the strategy returned +28.61% on $100,000 in starting capital. It still finished 47.72 points behind SPY buy-and-hold, and the tails are lopsided: the worst trade lost 10.43% against a best of 3.95%.
How a majority of winners produced that gap is the substance of the breakdown below.
Buy ET at the close when its daily news-sentiment score is in the bottom quintile of its prior 20 sessions while Brent crude closes above its 20-day simple moving average; exit when ET closes above its 5-day simple moving average or after 5 trading days, whichever comes first. Negative midstream headlines hitting a firm crude tape mark a sentiment flush rather than a cash-flow break, so ET snaps back once the forced selling clears.
How this was measured
This is a simulated backtest generated from the plain-English strategy below, executed bar-by-bar on historical market data using the price + news data mode with $100,000 starting capital. Strategy: Buy ET at the close when its daily news-sentiment score is in the bottom quintile of its prior 20 sessions while Brent crude closes above its 20-day simple moving average; exit when ET closes above its 5-day simple moving average or after 5 trading days, whichever comes first. Negative midstream headlines hitting a firm crude tape mark a sentiment flush rather than a cash-flow break, so ET snaps back once the forced selling clears.
The key numbers
The charts
The takeaway
The strategy returned +28.61% on $100,000 starting capital across 94 closed trades with a 59% win rate. Over the same window SPY buy-and-hold returned +76.34%, so the strategy finished trailing the benchmark by 47.72 points. Best single trade +3.95%, worst -10.43%.
The fine print
- Simulated results on historical data — fills, slippage and costs are idealized.
- Past performance does not predict future results.