Backtest: Buy XOM at the close when its daily news-sentiment score is in the bottom qui...
The setup sounds like contrarian bait: buy Exxon Mobil when its news sentiment is at its worst, as long as the stock still closes in the top half of its range. Bad headlines get absorbed; once the flow fades, the supermajor snaps back. Testing that on $100,000 across 80 closed trades returned +30.48% with a 51% win rate.
Profitable, but not compelling. SPY buy-and-hold returned +76.34% over the same window, so the strategy trailed by 45.86 points. Wins and losses stayed tight, and the edge came from repetition rather than any single outsized trade.
The full breakdown — every entry, exit, equity curve, and what the sentiment signal actually captured — is in the analysis below.
Buy XOM at the close when its daily news-sentiment score is in the bottom quintile of its prior 20 sessions but XOM closes in the top half of its daily range; exit when XOM closes below its 5-day simple moving average or after 5 trading days, whichever comes first. Negative XOM-specific headlines being bought into marks headline-driven selling that has been absorbed, so the supermajor tends to snap back once the news flow fades.
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 prior 20 sessions but XOM closes in the top half of its daily range; exit when XOM closes below its 5-day simple moving average or after 5 trading days, whichever comes first. Negative XOM-specific headlines being bought into marks headline-driven selling that has been absorbed, so the supermajor tends to snap back once the news flow fades.
The key numbers
The charts
The takeaway
The strategy returned +30.48% on $100,000 starting capital across 80 closed trades with a 51% win rate. Over the same window SPY buy-and-hold returned +76.34%, so the strategy finished trailing the benchmark by 45.86 points. Best single trade +7.11%, worst -3.80%.
The fine print
- Simulated results on historical data — fills, slippage and costs are idealized.
- Past performance does not predict future results.