The thesis
News-sentiment runs a simple, legible rule: buy names on positive recent news sentiment and exit on negative. It trades a 24-stock large-cap universe spanning tech (AAPL, MSFT, GOOGL, NVDA), financials (JPM, BAC, V, MA), healthcare (JNJ, UNH, PFE, ABBV), staples (PG, KO, WMT, COST), and a handful of consumer, energy, and industrial names (MCD, NKE, HD, XOM, CVX, CAT, HON, DIS). The appeal is interpretability — every entry and exit should map to a readable catalyst. The strategy is currently live.
Recent activity
The last executed orders were on 23 September 2026: a 4-share NVDA buy at $225.34 and a 35-share BAC sell at $55.96, closing a position opened on 12 June at $55.93 — essentially a round-trip at breakeven. Since then it has gone quiet. The six most recent scheduled runs (7–14 October) executed nothing; three of them (8, 9, and 12 October) each had a single order rejected. Cash has sat unchanged at $2,036.71 across all six, with total account value drifting between roughly $10,318 and $10,467 purely on existing holdings. The sentiment signal simply has not cleared the bar to act in weeks.
Backtest and validation
The backtest is where enthusiasm should cool. Over 451 days it returned +0.19% (CAGR 0.1%, final equity $10,018.55) on just 2 trades, with a Sharpe of 0.74, a trivial 0.05% max drawdown, 36.53% turnover, and $2 in total fees. Win rate is reported as 0% — difficult to square with a positive return, and a flag that round-trip accounting here is thin to the point of being noisy.
Validation failed. Across four walk-forward folds, only fold 4 (Dec 2025–May 2026) traded at all; folds 1–3 produced zero trades and zero return. That lone active fold did look good in isolation (+0.19%, Sharpe 1.5), but it means the full-sample and out-of-sample figures are identical by construction — all the evidence lives in one window. Against 6 trials, the probabilistic Sharpe (PSR 0.923) is encouraging, but the deflated Sharpe (DSR 0.551), the 1-of-4 positive-fold count, and the failed gate together say the edge is unconfirmed.
Strengths and risks
Strengths: the approach is disciplined and capital-preserving — tiny drawdown, near-zero fees, low turnover, and a willingness to reject orders rather than force trades. In its one active fold the risk-adjusted return was genuinely strong.
Risks: the sample is far too small to trust. Two trades cannot support a performance claim, three-quarters of the backtest window was inert, and the strategy has not fired in weeks of live running. The failed validation and modest DSR suggest any apparent edge may not survive out of sample.
Verdict: a sensible thesis that has not yet earned conviction. Keep it live at small size, but treat every current metric as provisional until trade count grows enough to mean something.