The thesis
channel-pullback is a hybrid trend-and-timing idea: it buys pullbacks to the lower regression channel or volume support within confirmed uptrends, then exits at the upper channel or resistance. In plain terms, it tries to buy dips in things that are already going up and sell into strength. The universe is 24 large-cap US names spanning tech, financials, healthcare, staples, and energy — a liquid, defensible opportunity set.
It is currently running live.
Recent activity
The last two weeks have been quiet. Scheduled runs from 2026-09-02 through 2026-09-09 executed at most one trade per day, with several days doing nothing at all. The visible trades cluster in BAC (a 31-share sell on 09-02, then a 30-share buy on 09-03 and 30-share sell on 09-09) and a string of small AAPL round-trips in late August, plus opening buys in UNH and JPM. These are short holds, consistent with the exit-at-resistance rule.
Less encouraging is the equity line: the paper account's total value drifted from $9,618.07 on 09-03 down to $9,394.71 on 09-09 — below a $10,000 starting stake. The live book is modestly underwater even as the backtest shows a gain.
Backtest and validation
Over 451 days the backtest returned 7.62% (CAGR 4.19%), ending at $10,761.52. But the risk-adjusted picture is weak: a Sharpe of 0.40, a 14.83% max drawdown, and a 39.39% win rate across 137 trades. The low win rate isn't fatal on its own — trend systems often win small and often lose — but combined with 2,311% turnover, this is a high-churn engine grinding out a thin edge.
Validation did not pass, and the fold-by-fold walk-forward shows why. Three of four folds were positive, but the range is violent: fold 3 returned +20.68% (Sharpe 3.86) while fold 2 lost -11.42% (Sharpe -1.70) with a 16% drawdown. That single bad regime swamps the average. Out-of-sample return was 3.63% (OOS Sharpe 0.74) — respectable, but the deflated Sharpe ratio of 0.196 is the number that matters most. After adjusting for the 7 trials run, the probability the true Sharpe exceeds zero is low; the probabilistic Sharpe (0.702) is decent but the DSR haircut is severe.
The balance
Strengths: a coherent, well-motivated thesis; a liquid universe; positive OOS return; and disciplined short holds. Fold 3 shows the strategy can genuinely rip when the regime suits it.
Risks: the edge is regime-dependent and fragile. A 39% win rate with 2,300% turnover means fees and slippage bite hard, the drawdown is real, and the deflated Sharpe suggests much of the apparent signal is trial-selection noise. The failed validation is the honest verdict — this is a strategy to watch on a small live allocation, not one to size up. Fold 2's collapse is the scenario to fear.