Thesis
The premise is simple and intuitive: buy names showing positive recent news sentiment and exit when the tone turns negative. It runs over a 24-stock large-cap universe spanning tech (AAPL, MSFT, GOOGL, NVDA), financials (JPM, BAC, V, MA), healthcare (JNJ, UNH, PFE, ABBV), and consumer and industrial staples. A defensible starting point — but a thesis only earns its keep once the trade record backs it up, and here the record is thin.
Recent Activity
Earlier in the summer the strategy was active, executing a handful of buys: AAPL at $312.06 (May 31), MSFT at $428.23 (Jun 3), BAC at $55.93 (Jun 12), UNH at $402.85 (Jun 18), and GOOGL at $360.40 (Jul 1). Since then it has gone quiet. Every scheduled run from September 10 through 17 executed zero trades, with orders repeatedly rejected — six runs, up to two rejections each, and not a single fill. The paper account sits around $10,270 total with $990.06 in cash, drifting between roughly $10,210 and $10,377 day to day. The engine is firing on schedule; the signals just aren't clearing whatever guardrails sit downstream.
Backtest and Validation
The backtest returned 0.19% over 451 days (final equity $10,018.55, CAGR ~0.1%) — essentially flat. The headline positive is risk: max drawdown was a slim 0.05% and turnover a modest 36.5%, at a trivial $2 in fees. But that calm comes from inactivity: the whole backtest logged just two trades, with a reported win rate of 0%.
Validation makes the fragility explicit — and it did not pass. Across four walk-forward folds, only one was positive. Folds 1 through 3 (Aug 2024 to Dec 2025) placed zero trades and returned zero. The entire 0.19% came from fold 4 (Dec 2025–May 2026), which posted a 1.5 out-of-sample Sharpe on all of two trades. In other words, every metric of merit rests on one short window and a two-trade sample.
The probabilistic gauges are mixed. The Probabilistic Sharpe Ratio is a healthy 0.923, but the Deflated Sharpe Ratio — which penalises for the 6 trials run — drops to 0.551, right at the coin-flip line. That gap is the honest read: adjust for how many variants were tested and the edge nearly vanishes.
Verdict
Strengths: tight drawdown control, low turnover, and negligible costs — this strategy will not blow up. Risks: it barely trades, its performance hangs on a single fold, it failed validation, and it is currently rejecting every order it generates. Right now news-sentiment reads less as a proven edge and more as a hypothesis awaiting enough live activity to test. The order-rejection pattern deserves investigation before any conclusions are drawn about the signal itself.