Backtest: Buy XOM at the close when its daily news sentiment score is in the bottom qui...
Bad news, a green close, and oil holding above its 20-day average: that combination is supposed to mark accumulation, the moment a bearish narrative gets rejected by price. So we tested it on XOM, buying the close when sentiment sat in the bottom quintile of its trailing 252 sessions, the stock still finished up, and Brent traded above its 20-day moving average.
The setup did produce snapbacks — 31 trades, +15.86% on $100,000, best single trade +7.96%. But only 43% of them worked, and the worst lost 3.85%. Over the same window, simply holding SPY returned +85.28%, leaving the strategy 69.41 points behind.
Whether that gap is a timing problem or a signal that rarely fires well is the question the full analysis below takes apart trade by trade.
Buy XOM at the close when its daily news sentiment score is in the bottom quintile of its trailing 252 sessions, XOM closes up on the day, and Brent crude closes above its 20-day simple moving average; exit when XOM closes below its 5-day simple moving average or after 5 trading days, whichever comes first. Bearish headlines being rejected by a positive close against a steady oil tape signal accumulation, so XOM tends to snap back once the narrative exhausts itself.
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 XOM at the close when its daily news sentiment score is in the bottom quintile of its trailing 252 sessions, XOM closes up on the day, and Brent crude closes above its 20-day simple moving average; exit when XOM closes below its 5-day simple moving average or after 5 trading days, whichever comes first. Bearish headlines being rejected by a positive close against a steady oil tape signal accumulation, so XOM tends to snap back once the narrative exhausts itself.
The key numbers
The charts
The takeaway
The strategy returned +15.86% on $100,000 starting capital across 31 closed trades with a 43% win rate. Over the same window SPY buy-and-hold returned +85.28%, so the strategy finished trailing the benchmark by 69.41 points. Best single trade +7.96%, worst -3.85%.
The fine print
- Simulated results on historical data — fills, slippage and costs are idealized.
- Past performance does not predict future results.