The thesis
The news-sentiment strategy runs a simple, intuitive rule: buy names showing positive recent news sentiment and exit when sentiment turns negative. It operates 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/industrial staples (PG, KO, WMT, COST, CAT, XOM, CVX). It is currently marked live.
Recent activity
The live paper account carries a total value of $10,499.14 against just $990.06 in cash — so it is close to fully invested. Its most recent executed trades were a cluster of buys between late May and early July: AAPL (6 sh @ $312.06), MSFT (4 @ $428.23), BAC (35 @ $55.93), UNH (4 @ $402.85), and GOOGL (5 @ $360.40).
Since then the engine has gone quiet. The last six scheduled runs (Jul 29–Aug 5) executed zero new trades, with a single rejected order on Aug 5. Portfolio value drifted between roughly $10,224 and $10,573 across those sessions, which tells us recent P&L is coming from mark-to-market on existing holdings, not from fresh signals.
Backtest and validation
Here the picture gets more sober. Over a 451-day backtest the strategy returned just +0.19% (final equity $10,018.55, ~0.1% CAGR) on only 2 trades, with a 0.05% max drawdown and a 0.74 Sharpe. Turnover was 36.5% and total fees $2. The headline number is thin because the model almost never trades.
Walk-forward validation makes that explicit — and it did not pass. Of four folds, three (Aug 2024 through Dec 2025) produced zero trades and zero return; the entire result comes from fold 4 (Dec 2025–May 2026), which logged 2 trades, +0.19%, and a 1.5 Sharpe. So foldsPositive is 1 of 4. The probabilistic Sharpe ratio (PSR 0.923) looks encouraging, but the deflated Sharpe (DSR 0.551), which penalizes for the 6 trials run, is far less convincing. Win rate reads 0.
The verdict
The strengths are real but modest: a tiny drawdown, a positive-if-negligible return, and a clean, explainable thesis. The risks dominate. This is a near-dormant strategy — a signal that fires so rarely that one fold carries the whole track record, which is the opposite of robust out-of-sample evidence. Until sentiment thresholds are loosened or the news feed starts producing more actionable signals, news-sentiment behaves less like an edge and more like a cash-heavy holding fund. It failed validation for good reason, and its live activity has stalled. The rejected Aug 5 order is the number to watch: it may hint that the entry bar is set too strictly rather than that the market has nothing to say.