Asked Sep 16, 10:10 AM EDT (morning session). DeepSeek V3 answered the same standard prompt independently. Window: from Sep 16, 10:10 AM EDT to Sep 17, 10:10 AM EDT, the same time one session later. Benchmark: SPY.
Five direction-adjusted close-to-close returns; a down call reverses the sign. The score is the mean signed return, without subtracting the benchmark. In each chart SPY is on the left and the picks on the right, every candle drawn from zero to that asset's move; ✓ marks a pick that moved the way it was called.
| Model | Correct | Hit rate | Return | SPY | Directional return |
|---|---|---|---|---|---|
| DeepSeek V3 | 3/5 | 60.00% | 2.54% | 0.07% | 2.54% |
DeepSeek V3
View full picks and reasoning
US equities closed lower on September 16, 2026, with the S&P 500 hitting a new August low as crypto-related stocks sold off sharply. Semiconductor and biotech names showed relative strength, while transportation and consumer discretionary lagged. I expect sector-specific catalysts to drive outperformance in select names over the next session, with merger-related news and index inclusion events providing the strongest signals.
- SWKS up — confidence 78%. Skyworks Solutions surged 13.55% on September 16 after CEO Philip Brace expressed strong confidence that the $22 billion Qorvo merger could close by late September or early October. The catalyst is substantive and merger-driven, with a confirmed timeline from management. The stock is rebounding from a prior 10%+ decline, suggesting continued momentum. Risk: any regulatory delay or negative merger development could reverse gains.
Return: -0.20%; alpha: -0.27%. - QRVO up — confidence 75%. Qorvo advanced 9.34% on September 16, moving in tandem with Skyworks on confirmed merger timeline news. The $22 billion merger creates a combined entity with significant scale in RF solutions. Catalyst is substantive and directly tied to M&A activity. Risk: merger arbitrage pressure or broader semiconductor sector weakness could limit upside.
Return: -0.22%; alpha: -0.29%. - ILMN up — confidence 72%. Illumina gained 6.76% on September 16 ahead of its imminent addition to the S&P 500 index, replacing Builders FirstSource before the market opens on September 21. Index inclusion is a substantive, calendar-driven catalyst that forces index-tracking funds to purchase shares. Risk: insider selling of $57M by a director may weigh on sentiment, and the stock could see profit-taking after the run-up.
Return: 6.12%; alpha: 6.05%. - INTC up — confidence 70%. Intel rose 5.45% on September 16 on reports that SK Hynix is exploring a partnership for US memory chip manufacturing, potentially at Intel's Ohio facility. The catalyst is substantive but speculative, as negotiations are early-stage. Intel's advanced process nodes (18A in production, 14A next year) add fundamental support. Risk: the partnership may not materialize, and the stock has fallen 7% over the past week.
Return: 6.42%; alpha: 6.34%. - KRUS up — confidence 65%. Kura Sushi USA plunged 14.01% on September 16, creating a potential oversold reversal opportunity. The decline appears driven by broader restaurant sector weakness and profit-taking after a strong run, rather than company-specific negative news. With a consensus price target of $66.40 versus the current $35.48, the risk-reward favors a bounce. Risk: continued sector rotation out of consumer discretionary could extend losses.
Return: 0.56%; alpha: 0.49%.
How models have done in Extreme Movers
ForecastNest's own settled Extreme Movers runs at this horizon, up to and including this one. Members' own research is not counted. Runs created after their scoring window began, or with an unverified start time, are excluded. The chart is the average directional return per run. A bar drawn pale is inside its own sample noise -- the runs behind it scatter too widely for that average to separate from zero -- so read the ordering as provisional until the record is deep enough to carry it. The table below adds how many of the five directions were called correctly, which is a steadier measure on a short record because it counts several picks a run rather than one result.
Chart note — “within noise”: The pale bar means the observed average is not clearly separated from zero by this chart's rule, or there is not enough information to assess it. A solid bar requires an average at least two standard errors from zero (standard error = sample standard deviation ÷ √runs). Fewer than two runs, missing variability, or zero measured variability remain pale. This is a rough uncertainty indicator, not proof of no effect or a guarantee of future performance.
| Model | Runs | Avg directions called correctly | Avg directional return |
|---|---|---|---|
| DeepSeek | 1 | 60.00% | +2.54% |
View settlement prices
| Symbol | Start | End | Source | Notes |
|---|---|---|---|---|
| ILMN | 227.52500000 | 241.45500000 | https://finance.yahoo.com/quote/ILMN/history/ | |
| INTC | 101.84500000 | 108.38000000 | https://finance.yahoo.com/quote/INTC/history/ | |
| KRUS | 35.75000000 | 35.95000000 | https://finance.yahoo.com/quote/KRUS/history/ | |
| QRVO | 116.12000000 | 115.86470000 | https://finance.yahoo.com/quote/QRVO/history/ | |
| SPY | 759.69000000 | 760.25000000 | https://finance.yahoo.com/quote/SPY/history/ | |
| SWKS | 87.70000000 | 87.52500000 | https://finance.yahoo.com/quote/SWKS/history/ |
Standard prompt extreme-movers-v7, SHA-256 0bbcd29bf74017571e73b91c9be19627d05cee21f05e155ec61b569cc8755883. The prompt is available to ForecastNest members; the fingerprint shows it was not changed after the fact.
Calculation: extreme-movers-v1.