Oct 14, 2026 - 7 AI models call the biggest movers in the morning session. 5 models finished positive

Asked Oct 14, 10:07 AM EDT (morning session). Gemini 3 Pro, Muse Spark 1.1, Grok 4, Perplexity, GPT-6, Claude Sonnet 5.5 and DeepSeek answered the same standard prompt independently. Window: from Oct 14, 10:07 AM EDT to Oct 15, 10:07 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
Gemini 3 Pro	1/5	20.00%	-1.18%	-0.79%	-1.18%
Muse Spark 1.1	3/5	60.00%	2.14%	-0.79%	2.14%
Grok 4	3/5	60.00%	2.12%	-0.79%	2.12%
Perplexity	2/5	40.00%	-0.33%	-0.79%	-0.33%
GPT-6	1/5	20.00%	1.20%	-0.79%	1.20%
Claude Sonnet 5.5	3/5	60.00%	1.94%	-0.79%	1.94%
DeepSeek	3/5	60.00%	1.67%	-0.79%	1.67%

Gemini 3 Pro

View full picks and reasoning

The US equity market on October 14, 2026, exhibits sector-specific volatility driven by third-quarter earnings reports, key macroeconomic inflation readings, and major corporate updates. Financials faced heavy selling pressure due to mixed profit prints and regulatory penalties, while specific asset managers and consulting firms experienced notable upside following strong earnings and strategic guidance updates.

1. BLK up — confidence 72%. BlackRock surged +3.87% in the source session following better-than-expected third-quarter profit and revenue figures. The catalyst is substantive, reflecting robust asset management inflows and earnings beat. Hypothesis is continuation given strong institutional momentum following the earnings release.
   Return: -1.07%; alpha: -0.28%.
2. STT down — confidence 68%. State Street dropped -7.62% in the source session after missing third-quarter revenue forecasts. The catalyst is substantive and fundamental. Hypothesis is continuation as institutional selling pressure often persists following a top-line miss in financial services.
   Return: 2.54%; alpha: -1.75%.
3. BAC down — confidence 65%. Bank of America sank -5.53% in the source session following a drop in third-quarter profit compounded by a $1.2 billion regulatory penalty and a wider-than-expected earnings miss. The catalyst is substantive. Hypothesis is continuation as regulatory overhang and earnings revisions weigh on near-term sentiment.
   Return: 4.08%; alpha: -3.29%.
4. ACN up — confidence 63%. Accenture gained +3.97% in the source session driven by investor focus on long-term AI monetization plans, growth guidance, and margin expansion targets presented during Investor Day. The catalyst is substantive. Hypothesis is continuation given strong strategic positioning in enterprise AI.
   Return: 2.77%; alpha: 3.56%.
5. FAST down — confidence 60%. Fastenal fell -5.29% in the source session after reporting third-quarter results in line with expectations but issuing a higher-than-expected capital expenditure outlook for 2026. The catalyst is substantive. Hypothesis is continuation as increased near-term capex concerns pressure equity valuations.
   Return: 0.96%; alpha: -0.17%.

Full prediction and audit record

Muse Spark 1.1

View full picks and reasoning

Oct 13 session was risk-off into CPI: energy/refiners outperformed on fuel tightness while tech equipment and defensives sold on rate fears. S&P -0.02% Nasdaq -0.15%. Expect mean reversion in crowded tech shorts and fade in energy spike into CPI print Oct 14.

1. VLO up — confidence 68%. Top gainer Oct 13 +4.69% close $456.46 on tight refining margins. Source session catalyst substantive: refinery capacity headlines. Ranking #1 large-cap gainer. Continuation up chosen as momentum in energy sector with crude bid. Reference price is Oct 14 intraday delayed quote 451.88 down 1.0% intraday, so slightly stale vs open but still latest available. Meets price >=5, market cap 124.89B and avg dollar volume ~1.5B >20M.
   Return: -0.62%; alpha: 0.17%.
2. ORCL down — confidence 62%. Gainer Oct 13 +4.23% to $143.20 on hardware security collaboration and AI cloud positioning. Substantive but speculative upside into CPI. Ranking #2 large-cap gainer. Reversal down expected as +4.23% was counter-trend in falling Nasdaq and intraday Oct 14 already showing -6.97% to 133.205 indicating fade. Uses Oct 14 intraday current price as reference.
   Return: -1.46%; alpha: 2.25%.
3. AMAT down — confidence 65%. Top loser Oct 13 -6.69% to $464.24 on investor day without industry spending forecast. Catalyst substantive negative for equipment. Ranking top large-cap loser. Continuation down expected as guidance gap weighs and sector weak 7-day. Reference price Oct 14 intraday 455.565 down another -1.86% showing follow-through. Market cap 402.38B and avg volume ~2.7B passes filters.
   Return: -7.64%; alpha: 8.43%.
4. JNJ up — confidence 60%. Loser Oct 13 -5.73% to $248.90 on earnings reaction despite YTD +22%. Catalyst substantive but overreaction in defensive pharma into CPI. Ranking #2 large-cap loser. Reversal up expected as defensive bid returns with inflation expectations at 4.7%. Reference price Oct 14 intraday 251.445 up +1.14% vs prior close, indicating intraday reversal already starting, used as latest quote.
   Return: 3.36%; alpha: 4.15%.
5. C up — confidence 58%. Loser Oct 13 -5.60% on bank earnings digestion ahead of CPI. Turnover 2.6B. Catalyst substantive: loan growth and trading income concerns. Ranking large-cap loser. Reversal up chosen as banks oversold vs 4.1B turnover and JPM peers stabilizing, CPI may relieve rate pressure. Reference price Oct 14 intraday 122.0 down -2.03% but near support. Market cap 217.46B passes, avg dollar volume ~1.8B >20M.
   Return: -1.14%; alpha: -0.35%.

Full prediction and audit record

Grok 4

View full picks and reasoning

Source session October 13 saw modest index declines with energy refiners leading gainers on elevated crude prices and supply concerns while healthcare and semiconductor names lagged on earnings and competitive pressures. Expect selective continuation in energy strength and selective mean-reversion in oversold large-cap defensives into the next session.

1. PBF up — confidence 68%. PBF closed the source session up 7.23 percent on sector-wide refining strength tied to higher crude and crack-spread optimism; continuation higher is favored as oil prices remain elevated and the name trades with strong volume. Reference price is the latest intraday quote near the open of October 14; market-cap and dollar-volume floors confirmed at source close. Catalyst is substantive sector momentum rather than company-specific news.
   Return: -2.49%; alpha: -1.70%.
2. PARR up — confidence 65%. PARR advanced 8.13 percent in the source session alongside peer refiners on the same crude-price tailwind; continuation is the base case given persistent energy leadership and liquid trading. Latest available price used for reference; all liquidity and size screens passed at the October 13 close. Catalyst is substantive sector rotation into refining.
   Return: -2.46%; alpha: -1.67%.
3. CVI up — confidence 62%. CVI rose 7.15 percent with the refining group on October 13; continuation expected while crude remains firm and relative volume stays healthy. Reference price reflects the most recent quote obtainable on October 14; market-cap and average dollar-volume thresholds met. Catalyst is the same substantive energy-sector move.
   Return: 0.55%; alpha: 1.34%.
4. FUN down — confidence 60%. FUN dropped 14.43 percent in the source session after a fatal roller-coaster incident raised liability and operational concerns; continuation lower is favored as the news is material and volume was elevated. Latest intraday price used; size and liquidity screens cleared. Catalyst is substantive company-specific negative event.
   Return: -11.65%; alpha: 12.44%.
5. JNJ up — confidence 58%. JNJ fell 5.73 percent on October 13 despite an adjusted earnings beat after MedTech sales missed and a large talc-related charge hit GAAP results; a partial reversal higher is expected as the miss is largely already priced and the name is a high-quality defensive. Reference price is the freshest available quote; all screening criteria satisfied. Catalyst is substantive earnings detail with some speculative over-reaction component.
   Return: 3.36%; alpha: 4.15%.

Full prediction and audit record

Perplexity

View full picks and reasoning

The source session is the intraday US session of October 14, 2026, with Nexqual mover data as of 13:56 UTC (09:56 ET). The tape shows sharp, catalyst-driven dispersion: Bank of America and Progressive are under pressure around earnings, Dell is selling off after a large prior run, while UnitedHealth and GlobalFoundries are advancing on company-specific news. I favor continuation in names with substantive, same-day catalysts and sufficient liquidity, while recognizing that intraday extreme moves often partially mean-revert by the next close.

1. BAC down — confidence 58%. Bank of America was down 8.18% intraday in the source session at $49.53, according to Nexqual's October 14 13:56 UTC mover list. The decline follows a substantive catalyst: the U.S. Treasury announced more than $1.21 billion in penalties related to anti-money-laundering and sanctions-compliance failures, and the bank said its Q3 results would include a $1.2 billion non-tax-deductible charge. Bloomberg also reported that FICC trading revenue excluding DVA missed the average analyst estimate. Because the news is fundamental rather than speculative, I expect continued pressure into the next close, though the size of the drop creates bounce risk. Reference price is the Nexqual intraday quote at 13:56 UTC on October 14, 2026. Market cap is the StockAnalysis figure of $377.33 billion; I could not independently verify the 20-day average dollar volume, so that field is omitted.
   Return: 4.08%; alpha: -3.29%.
2. PGR down — confidence 52%. Progressive fell 9.49% intraday to $201.74 in the source session, per Nexqual's October 14 13:56 UTC list. The stock reported Q3 results on October 14, and the sharp decline suggests the market judged the report unfavorably; this is a substantive earnings catalyst rather than a technical move. With the decline already large, some stabilization is possible, but I judge continuation lower more likely than a full next-session reversal. Reference price is the Nexqual intraday quote at 13:56 UTC on October 14, 2026. Market cap is the StockAnalysis figure of $129.58 billion; the 20-day average dollar volume was not independently verified and is omitted.
   Return: 7.98%; alpha: -7.19%.
3. DELL down — confidence 50%. Dell Technologies declined 7.12% intraday to $531.56 in the source session, according to Nexqual's October 14 13:56 UTC mover list. The stock had been one of 2026's strongest AI-infrastructure performers, and the pullback appears to be a valuation and momentum-driven correction within a broader chip and AI-hardware selloff rather than a new company-specific negative disclosure. Given the extended rally and the absence of a clear positive offsetting catalyst, I expect continued weakness, while acknowledging high reversal risk after a large one-session drop. Reference price is the Nexqual intraday quote at 13:56 UTC on October 14, 2026. Market cap is the StockAnalysis figure of $363.98 billion; the 20-day average dollar volume was not independently verified and is omitted.
   Return: -12.64%; alpha: 13.43%.
4. UNH up — confidence 51%. UnitedHealth Group rose 3.88% intraday to $392.41 in the source session, per Nexqual's October 14 13:56 UTC list. The move follows its October 13 Q3 earnings report, making this a substantive post-earnings re-rating rather than a purely speculative rally. The stock had been under pressure into the print, so a positive earnings reaction can continue as analysts update estimates and positioning adjusts. The principal risk is post-earnings profit taking after the initial pop. Reference price is the Nexqual intraday quote at 13:56 UTC on October 14, 2026. Market cap is the StockAnalysis figure of $339.76 billion; the 20-day average dollar volume was not independently verified and is omitted.
   Return: 4.84%; alpha: 5.63%.
5. GFS up — confidence 49%. GlobalFoundries gained 4.54% intraday to $48.82 in the source session, according to Nexqual's October 14 13:56 UTC list. The move extends a substantive catalyst from earlier in the week: a multi-year, approximately $2 billion agreement to manufacture silicon interposers for TSMC's advanced AI-packaging ecosystem in New York. That agreement supports the AI infrastructure demand narrative and gives the rally a fundamental basis, so I favor continuation, though semiconductor sentiment was weak elsewhere in the session and could cap the follow-through. Reference price is the Nexqual intraday quote at 13:56 UTC on October 14, 2026. Market cap is the StockAnalysis figure of $25.63 billion; the 20-day average dollar volume was not independently verified and is omitted.
   Return: -7.06%; alpha: -6.27%.

Full prediction and audit record

GPT-6

View full picks and reasoning

The October 13, 2026 session showed sharp dispersion despite relatively flat major indexes. Refining stocks rallied on substantial global fuel supply constraints and unusually strong diesel refining margins, while company-specific negative events drove large losses elsewhere. For the October 14-15 forecast window, I favor selective continuation in fundamentally supported refinery winners, further weakness in Six Flags following a material safety incident, a technical rebound in Arcus Biosciences, and profit-taking in the most overextended refining name. The refinery selections are positively correlated, creating concentrated exposure to changes in fuel margins, crude prices, and geopolitical developments. All five stocks met the October 13 closing-session screening thresholds. The 20-day dollar-volume figures are calculated estimates using the arithmetic mean of daily closing price multiplied by daily share volume for the 20 completed sessions ending October 13, rather than verified exchange-reported VWAP dollar turnover. Reference prices are October 14 intraday observations with their individual timestamps disclosed. The scoring period is already underway; these observations do not constitute knowledge of its final result. The signed directional return and direction accuracy remain unknown until the forecast window closes.

1. FUN down — confidence 72%. Six Flags Entertainment declined 14.43% during the October 13 regular session, closing at $10.20. It ranks first because its decline followed a substantive and potentially persistent negative catalyst: a fatal roller-coaster incident at Six Flags Over Georgia, followed by precautionary closures of nine similar rides. Associated investigations, litigation exposure, reputational damage, and potential operational disruption during the important Halloween season create risks extending beyond a single trading day. Financial leverage and already weak operating performance amplify downside sensitivity. Associated Press and MarketWatch independently reported the incident and operational response. The latest verified intraday quote was $9.65 at 10:09 AM EDT on October 14, approximately one minute before the initial research snapshot, representing additional selling pressure. This is a continuation forecast relative to October 13's negative return, not a prediction about the opening gap. The October 13 market capitalization was approximately $1.04 billion, satisfying the required floor at the source-session close, although the subsequent intraday capitalization fell below $1 billion. The principal opposing risk is an oversold rebound, especially given substantial short interest. Historical price and volume records: https://stockanalysis.com/stocks/fun/history/ . Incident reporting: https://apnews.com/article/a9ce45f681772b828f7b5d3c59d010d1 . The 20-day dollar-volume figure is calculated from historical closing prices and volumes.
   Return: -11.65%; alpha: 12.44%.
2. PARR up — confidence 64%. Par Pacific Holdings gained 8.13% on October 13, closing at $89.88. It ranks second because the advance is associated with substantive industry economics rather than an isolated speculative announcement. Global refinery disruptions, constrained diesel supply, and favorable product crack spreads support profitability for U.S. refiners. Par Pacific offers direct exposure to this environment through its refining operations. Recent analyst commentary has also recognized strong refining fundamentals, although Mizuho downgraded the shares to Neutral on valuation. The latest verified October 14 intraday price was $88.53 at 10:02 AM EDT, a several-minute-old observation showing early profit-taking. I nevertheless forecast positive continuation from the original source-session gain because elevated refining margins may sustain demand for shares after the initial rotation. Risks include falling product margins, reversal of geopolitical supply disruptions, broad market weakness, and the recent downgrade. The October 13 closing market capitalization was $4.50 billion. Historical closing prices and volumes support the estimated 20-day dollar liquidity. Industry evidence: https://www.wsj.com/business/energy-oil/american-oil-refiners-are-printing-money-as-wars-shrink-global-energy-supplies-c9240231 . This is an industry-supported catalyst, not a verified new company-specific development on October 13.
   Return: -2.46%; alpha: -1.67%.
3. PBF up — confidence 62%. PBF Energy advanced 7.23% during the October 13 regular session, closing at $91.17. It ranks third because its sizable gain is supported by substantive sector fundamentals: constrained global refining capacity, strong diesel pricing, and expectations of elevated U.S. refining profitability. Reports also describe refining-sector analyst target increases, but no company-specific filing was verified as the direct cause of this session's jump. The latest verified October 14 intraday quote was $90.25 at 9:58 AM EDT, approximately ten minutes before the initial research snapshot. This indicates moderate early profit-taking following the prior advance. The continuation thesis assumes refining margin strength outweighs short-term profit realization during the scoring window. The main risks are exceptionally strong prior stock performance, a reversal in refining spreads, reported significant shareholder selling, and sensitivity to crude-price and geopolitical developments. The October 13 market capitalization was approximately $10.89 billion, with substantial 20-day estimated dollar liquidity. Supporting sector coverage: https://www.wsj.com/business/energy-oil/american-oil-refiners-are-printing-money-as-wars-shrink-global-energy-supplies-c9240231 . The industry catalyst is fundamental, but the exact single-day price response includes sentiment and positioning effects.
   Return: -2.49%; alpha: -1.70%.
4. RCUS up — confidence 55%. Arcus Biosciences declined 7.52% on October 13, closing at $22.51. It ranks fourth as a potential short-term reversal candidate following a large decline without a verified new company-specific clinical failure or material adverse filing on that date. The identifiable background catalysts are more speculative and positioning-driven: profit-taking before an October 20 investor event featuring casdatifan data, concern about concentrating development value in that asset, and the earlier wind-down of the Gilead-partnered domvanalimab program. Those are real fundamental uncertainties, but none was confirmed as a new October 13 announcement causing the entire move. The latest verified October 14 intraday quote was $22.83 at 9:37 AM EDT, approximately 30 minutes before the research snapshot, showing an initial rebound. I favor a modest upward reversal rather than another full session of selling. Risks include further biotechnology-sector weakness, adverse expectations for the upcoming data presentation, and financing concerns associated with ongoing research spending. The October 13 market capitalization was $2.87 billion. Background reporting: https://www.tipranks.com/news/catalyst/arcus-biosciences-tumbles-as-investors-bail-early . The hypothesis is lower confidence because the source-session decline lacks a verified singular catalyst.
   Return: -0.17%; alpha: 0.62%.
5. CVI down — confidence 60%. CVR Energy gained 7.15% on October 13, finishing at $63.12. It ranks fifth because the powerful refining-sector rally creates an opportunity for a short-term negative reversal after an unusually extended advance. The underlying sector catalyst is substantive: tight global refined-product supplies and exceptionally favorable refining margins. However, no fresh company-specific filing explaining the October 13 surge was identified. CVI's relative strength index was approximately 81, indicating technically overextended conditions, and its preceding 52-week performance was already substantial. The latest verified October 14 intraday quote was $62.35 at 10:00 AM EDT, several minutes before the research snapshot, showing that profit-taking had begun. I forecast a negative next-session directional return despite recognizing that strong refining economics could remain favorable for multiple quarters. The opposing risk is another rapid increase in diesel margins or geopolitical supply concerns, which could produce further upside. The October 13 market capitalization was $6.35 billion, and estimated 20-day dollar liquidity comfortably exceeded $20 million. Industry coverage: https://www.theguardian.com/business/2026/oct/14/refineries-record-profits-diesel-shortage-fuel-crude-oil . The catalyst is fundamental at the industry level; the forecast reversal is a technical and positioning hypothesis.
   Return: 0.55%; alpha: 0.24%.

Full prediction and audit record

Claude Sonnet 5.5

View full picks and reasoning

The S&P 500 finished the Oct 13 source session flat at 7,805.45. Underneath, earnings reactions and sector rotation were large: memory chips fell on China's CXMT progress, IT services rebounded, and several earnings losers sold off despite headline beats. Next-session outcomes are likely to hinge on post-earnings drift and whether the chip and software pullbacks stabilize. I could not find a live Oct 14 regular-session quote for every pick, so each rationale says which price I used and how stale it is.

1. JNJ up — confidence 58%. JNJ fell 5.73% on Oct 13 even though Q3 sales and adjusted EPS beat and full-year guidance was raised. The selloff centered on weak MedTech growth and one-time charges (talc settlement, acquisitions). The catalyst looks substantive but the reaction looks overdone for a low-beta $599B pharma-heavy mega-cap. After-hours trading was slightly higher, and BofA raised its target to $282. Reference price is the Oct 13 regular-session close (about one session stale); I found no Oct 14 intraday quote. Market cap is from Yahoo Finance; 3-month average volume of about 7.1M shares clearly exceeds the dollar-volume floor, but I did not find a stated 20-day dollar-volume figure, so that field is omitted. Risk: the MedTech spin-off and talc overhang may keep the stock heavy.
   Return: 3.36%; alpha: 4.15%.
2. DPZ down — confidence 55%. DPZ fell 4.76% on Oct 13 after Q3 US same-store sales growth missed estimates. Several analysts cut price targets (Guggenheim to $325 from $440; Morgan Stanley to $357 before the report). Free-cash-flow and cash-flow trends weakened and refinancing interest costs are rising. Substantive catalyst, so I expect post-earnings drift to continue lower, although the stock sits near support in the low $290s. Reference price is the Oct 13 close, about one session stale. Market cap is likely near $10B (about 33M shares) but I did not find a figure for that date, so it is omitted. Share volume of roughly 800K per day implies well over $20M in daily dollar volume, but I did not find a stated dollar-volume figure, so that field is omitted. Risk: a bounce from the 52-week low area.
   Return: 5.08%; alpha: -4.29%.
3. INFY up — confidence 52%. INFY gained 5.26% on Oct 13 in a broad IT-services rally led by Indian peers (HCL, TCS, Tech Mahindra). It is still near the bottom of its 52-week range, so the move looks like a sector re-rating rather than company news (a mixed substantive/speculative catalyst). A pre-market quote of 11.54 on Oct 14 suggests follow-through. Reference price of 11.47 is the latest quote I found for Oct 14 (delayed or pre-market, not verified as a regular-session print). Market cap is from Morningstar; the roughly 20M-share average volume at about $11.4 clears the dollar-volume floor, but a stated 20-day dollar-volume figure was not found, so that field is omitted. Risk: earnings on Oct 22 and fading of the sector bounce.
   Return: 5.11%; alpha: 5.90%.
4. GTLB down — confidence 52%. GTLB fell 7.25% on Oct 13 to $51.95 on heavy volume (9.2M versus a 4.6M average). The cause was a maximum-severity CVE in its self-managed products (patched) after a big run-up toward its 52-week high. The catalyst is partly speculative, but after-hours trading was down a further 4.3% and pre-market was about $2.31 lower. I used about 49.64, computed as the $51.95 close minus the reported $2.31 pre-market decline, so it is a pre-market estimate rather than a regular-session print. Market cap is from Yahoo Finance; volume at about $50 per share clears the dollar-volume floor, but a stated 20-day dollar-volume figure was not found, so that field is omitted. Risk: patched-vulnerability headlines fade and dip buyers step in.
   Return: 0.55%; alpha: 0.24%.
5. MU down — confidence 50%. MU fell 3.62% on Oct 13 to $953.19 as memory stocks sold off on China's CXMT progress on a denser memory architecture, a sector-wide valuation concern. The stock is in bear-market territory (more than 23% below its high), and the selling is described as crowded positioning, so I expect pressure to persist. This is a low-conviction call: the stock is cheap on forward earnings (about 5x) and could rebound sharply. Reference price is a pre-market quote of 945.50 for Oct 14, not a regular-session print. Market cap of about $1.08T and average volume of 25.6M to 32M shares at roughly $950 clear the floors easily; no stated 20-day dollar-volume figure was found, so that field is omitted. Risk: sharp mean reversion.
   Return: -6.86%; alpha: 7.65%.

Full prediction and audit record

DeepSeek

View full picks and reasoning

The 13 October 2026 US session was split: a semiconductor-equipment and chip selloff dragged the Nasdaq lower (Nasdaq -0.15%, S&P 500 -0.02%, Dow -0.35%) while refining/energy and IT-services names rallied hard and blue-chip Johnson & Johnson was punished on a MedTech miss. For the 14 October target session I expect the refining momentum (strong crack spreads, tight product supply) to carry into a second day, Indian IT ADRs to extend their rebound after HCL Tech's strong print, semiconductor-equipment weakness to persist one more session after Applied Materials' investor day gave no industry spending forecast, and GitLab to bounce after a technical/insider-selling overreaction. My five picks are all close-to-close views from the 13 October close to the 14 October close; three are continuation-up in energy/IT, one is continuation-down in semi-cap equipment, and one is a reversal-up in software.

1. PARR up — confidence 62%. Par Pacific jumped 8.13% on 13 October to a 52-week high of $90.17, closing at $89.88, as the refining group rallied on tight product supply and strong crack spreads; TipRanks reported the move was driven by a more optimistic refining-margin and fuel-demand outlook plus anticipation of the 3 November Q3 release, and peer PBF also set a 52-week high. I judge this a substantive, margin-driven catalyst, not a speculative squeeze, so I take continuation up. reference_price $90.32 is the freshest quote I could confirm (Robinhood, 14 October, intraday); stockanalysis.com showed an after-hours print of $90.26 on 13 October. The stock is extended (RSI high, Mizuho cut it to Neutral on valuation with a $91 target), so a same-day fade is the main risk. Market cap and 20-day dollar volume were checked and both clear the floors.
   Return: -2.46%; alpha: -1.67%.
2. PBF up — confidence 60%. PBF Energy rose 7.23% on 13 October to a new 52-week high of $91.53, closing at $91.17 on roughly 3.4 million shares, riding the same refining-margin/crack-spread theme as PARR; Mizuho raised its price target to $89 from $65. The catalyst is substantive (industry margin outlook), so I take continuation up. reference_price $91.50 is the 14 October intraday quote from Robinhood, with stockanalysis.com showing an after-hours print of $91.50 on 13 October; data_date reflects the quote date. The main risk is that the name is very extended (+229% over 52 weeks, RSI ~68) and a one-day mean-reversion after a 52-week-high breakout is plausible. Market cap and 20-day dollar volume were verified above the floors.
   Return: -2.49%; alpha: -1.70%.
3. INFY up — confidence 58%. Infosys ADR rose 5.26% on 13 October to close at $11.40 as Indian IT ADRs spiked after HCL Tech's strong earnings lifted the whole sector (Nifty IT +3-5%); Q2 results are due 23 October. I read the catalyst as substantive sector momentum rather than a one-day technical blip, so I take continuation up. reference_price $11.50 is the latest intraday quote I could confirm (Robinhood, 14 October); the 13 October regular-session close was $11.40 and Yahoo showed a $11.50 after-hours print the same evening, so I used the fresher 14 October figure and set data_date accordingly. The main risk is that the ADR is in a longer downtrend (-32% over one year) and the rebound could fade. Market cap and 20-day dollar volume were verified above the floors.
   Return: 5.11%; alpha: 5.90%.
4. AMAT down — confidence 57%. Applied Materials fell 6.69% on 13 October to $464.24 (intraday low $452.81), its sixth straight losing session, after its Investor Day presentation at SEMICON West failed to provide a specific industry spending forecast; Investing.com and The Motley Fool both framed the drop as disappointment over uncertain 2030/industry guidance, and the stock is down about 15% since 5 October. I view the negative catalyst as substantive for the near term and take continuation down, even though Evercore/Cantor remain long-term bullish. reference_price $469.00 is the 14 October pre-market print from stockanalysis.com; I could not obtain a firm 14 October regular-session intraday quote, so the fresher pre-market figure is used with data_date 2026-10-14. The obvious risk is an oversold bounce after six down days. Market cap and 20-day dollar volume clear the floors by a wide margin.
   Return: -7.64%; alpha: 8.43%.
5. GTLB up — confidence 52%. GitLab fell 7.25% on 13 October to $51.95 after touching a 52-week high of $57.89, with the selloff attributed to profit-taking, technical deterioration and insider selling (Goldman Sachs flagged AI-monetization uncertainty; the CFO trimmed a stake worth about $1.6 million) rather than a fundamental earnings miss. By early on 14 October the stock had reversed higher (+4.41% to $54.24 in the early session, and an intraday print near $54.56), which I read as a reversal of an overdone technical move, so I take reversal up. reference_price $54.24 is the early-session 14 October quote from the cited Finet report; data_date reflects that quote. Data quality here is the weakest of my five picks: Yahoo showed a 13 October after-hours print near $49.94 and Robinhood showed a $50.15 figure, so the 14 October path was volatile and my price could not be fully reconciled across vendors. Market cap and 20-day dollar volume were verified above the floors.
   Return: 0.55%; alpha: 1.34%.

Full prediction and audit record

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
Claude Sonnet 5.5	10	58.00%	+0.99%
Grok 4	3	53.33%	+0.92%
Meta AI - Muse Spark	1	40.00%	+0.73%
DeepSeek	21	48.57%	+0.68%
Grok 4.5	15	49.33%	+0.29%
Claude Opus 5	6	60.00%	+0.03%
Gemini 3 Pro	3	46.67%	-0.19%
Muse Spark 1.1	18	40.00%	-0.22%
Claude Opus 5.5	3	33.33%	-0.24%
Perplexity	14	42.86%	-0.36%
Gemini 1.5 Pro	17	48.24%	-0.59%
GPT-6	9	46.67%	-0.97%
GPT-5.6 Sol	10	46.00%	-3.06%

View settlement prices

Symbol	Start	End	Source	Notes
ACN	217.76000000	223.79000000	https://finance.yahoo.com/quote/ACN/history/
AMAT	455.57500000	420.77000000	https://finance.yahoo.com/quote/AMAT/history/
BAC	49.34990000	51.36500000	https://finance.yahoo.com/quote/BAC/history/
BLK	1085.01000000	1073.37000000	https://finance.yahoo.com/quote/BLK/history/
C	121.96750000	120.58000000	https://finance.yahoo.com/quote/C/history/
CVI	61.78000000	62.12000000	https://finance.yahoo.com/quote/CVI/history/
DELL	529.88000000	462.91370000	https://finance.yahoo.com/quote/DELL/history/
DPZ	287.00000000	301.57000000	https://finance.yahoo.com/quote/DPZ/history/
FAST	49.99000000	50.47000000	https://finance.yahoo.com/quote/FAST/history/
FUN	9.74000000	8.60500000	https://finance.yahoo.com/quote/FUN/history/
GFS	49.46000000	45.97000000	https://finance.yahoo.com/quote/GFS/history/
GTLB	53.39500000	53.69000000	https://finance.yahoo.com/quote/GTLB/history/
INFY	11.45000000	12.03500000	https://finance.yahoo.com/quote/INFY/history/
JNJ	251.44250000	259.89000000	https://finance.yahoo.com/quote/JNJ/history/
MU	942.53000000	877.85000000	https://finance.yahoo.com/quote/MU/history/
ORCL	133.22000000	131.27000000	https://finance.yahoo.com/quote/ORCL/history/
PARR	88.12010000	85.95000000	https://finance.yahoo.com/quote/PARR/history/
PBF	89.01750000	86.80000000	https://finance.yahoo.com/quote/PBF/history/
PGR	201.91000000	218.02000000	https://finance.yahoo.com/quote/PGR/history/
RCUS	23.14000000	23.10000000	https://finance.yahoo.com/quote/RCUS/history/
SPY	773.07000000	766.96000000	https://finance.yahoo.com/quote/SPY/history/
STT	159.74750000	163.81000000	https://finance.yahoo.com/quote/STT/history/
UNH	388.70500000	407.51500000	https://finance.yahoo.com/quote/UNH/history/
VLO	452.16000000	449.33500000	https://finance.yahoo.com/quote/VLO/history/

Standard prompt extreme-movers-v11, SHA-256 91a15b54b411156a187fa4f237ff8c51c42b45c98f97b24c67ed619acdfcf4d8. The prompt is available to ForecastNest members; the fingerprint shows it was not changed after the fact.

Calculation: extreme-movers-v1.