Curated, opinionated filters that run on a cron — Stage 2, trend templates, fundamentals. Subscribe to receive results in your inbox and via Telegram, or pull them through the JSON API.
When a big story hits one company, the company economically attached to it often has not reacted yet. This board reads the platform's 38,000-edge relationship graph — typed, directional, evidence-backed supplier / customer / partner / competitor links extracted from news — and finds those un-reacted neighbours. The hard part is not finding connections; it is the three ways this strategy loses, each of which is a filter here rather than a judgement call: 1. THE NEIGHBOUR HAS ALREADY MOVED. This is a PRICE question, not a news question — sympathy selling moves a stock without generating a single article, so quiet coverage proves nothing. Each candidate's return over the window is compared with the headline's, and anything that has already collected a meaningful share of the move (in either direction) is dropped. 2. THE SIGN IS BACKWARDS. Edge direction in the graph is unambiguous — `from -[supplier]-> to` means from SUPPLIES to — so the rule is arithmetic: everyone in a value chain moves WITH the headline, a competitor moves AGAINST it. 3. THE EDGE IS TOO SMALL TO MATTER. A real relationship touching 2% of revenue is a fact, not a trade. Edges are gated on strength and on how many independent articles asserted them. Pipeline: 1. Headline names: enough coverage in the last few days to be a real story, and either a strongly one-directional sentiment reading or a large price move. Both are reported, because they disagree more often than you would expect — one recent story ran at +0.31 average sentiment across 75 articles while the stock fell 15%, and a sentiment-only screen would have pointed the wrong way. 2. Neighbours: every graph edge above a strength and mention floor, deduplicated to ONE edge per pair (the graph stores both directions and sometimes several types for the same pair). 3. Tradeable: US-listed and liquid enough to enter and exit; the raw graph contains foreign listings that no order could fill. 4. Sign, then the not-yet-moved test. 5. Contradictions dropped: a name that two live stories push in OPPOSITE directions is removed rather than resolved, because it has no second-order edge left. Several stories pushing the same way are kept as corroboration. Each row carries the headline and its move, the neighbour and its move, the share of the move already captured, the edge type / strength / evidence count, and the resulting side.
Michael Burry's documented method, run on both sides of the book. Half of it is a conventional value screen — EV/EBITDA (industry-relative, as Burry describes it), free cash flow, low debt, enterprise value rather than market cap. The other half is the part a conventional screener cannot run at all: Burry looked for "ick" stocks that provoke revulsion, and for the neglected — "unpopular companies that look like road kill". Those are facts about ATTENTION and SENTIMENT, and this platform measures both per ticker per day. Over a 90-day window across ~3,885 covered tickers, sentiment runs p10 -0.28 / median +0.41 / p90 +0.80. It skews strongly positive, so a negative reading is genuinely rare — which is what makes "ick" a discriminating gate rather than a mood. Pipeline (cheap gates first; the fundamental step costs one API call per survivor): 1. Attention gates, one query. LONG — 90-day average sentiment below zero AND mention count inside a neglect band (enough coverage to be real, little enough to be ignored). SHORT — sentiment above +0.60 AND heavily covered. 2. Liquidity floor: enough price and volume to take and exit a position. 3. Value gates, per survivor: LONG — EV/EBITDA under a SECTOR-relative ceiling (tech 18x … energy 8x), free cash flow yield above 4%, net debt / EBITDA under 3.5x. SHORT — EV/EBITDA above 1.5x the sector ceiling AND free cash flow yield under 2%: rich on the multiple and not generating the cash to justify it. A rich multiple on strong cash flow is a good business, not a short. 4. Rare-bird flag (not a gate): working capital per share above the price — Burry's "selling at less than two-thirds of net value". Flagged when found, because those deserve longer holding periods. 5. Margin of safety, where available: the priced-in programme's reverse-DCF. median_gap says where the price sits against published analyst models; implied_revenue_cagr says what growth the price REQUIRES. Only ~476 names carry one, so it annotates rather than gates — requiring it would cap the board at the large-cap end and exclude exactly the neglected names the screen exists to find. NO market-regime gate, unlike NIS Short. Gating on the S&P's 200-day is O'Neil's timing discipline; Burry is early on purpose and holds through the drawdown. This is deliberately NOT the NIS Short method. That board shorts former leaders in a Stage-4 breakdown, entered 5-15 weeks after the top. This one shorts what is expensive, adored and crowded while it is still going up. Known gap: short interest / days-to-cover is not available, so squeeze risk on the short side is unscreened — the same hole NIS Short documents. Rows carry a `side` field so one run answers both questions.
Stocks positioned to benefit from persistently high inflation and higher-for-longer rates — precious metals, energy, commodities & materials, pricing-power staples, energy infrastructure, rate-beneficiary financials and inflation-protected proxies — each validated by price momentum and real inflation-news exposure.
Stocks positioned to benefit from an Iran / Strait-of-Hormuz supply shock — oil & gas, oil services, defense & aerospace, tankers & shipping, uranium & energy security, and safe-haven — each validated by price momentum and real crisis-news exposure.
The short-side inverse of NIS Momentum, applying Minervini SEPA / O'Neil CAN SLIM to the SHORT side. Targets FORMER LEADERS rolling over into a Stage-4 decline — distribution and failure — not perennial losers already at new lows. The whole screen is gated on a bearish market regime (only runs when the S&P is below its 200-day). Pipeline: 0. Market regime gate: skip entirely unless the S&P 500 is below its 200-day MA. 1. Universe: all listed NYSE + NASDAQ tickers. 2. Inverted pre-screen: actively traded, price < SMA200, SMA50 < SMA200, at least 25% below the 52-week high, AND weak RS (bottom ~30%, RS < 30). 3. Stage-4 decline template — all conditions required: • close < SMA50 < SMA150 < SMA200 • SMA200 falling (20-day slope confirmation) • close at least 25% below the 52-week high, and that high is stale (made months ago — peak at least ~5 weeks old) • RS weak (RS < 30 — the inverse of the long side's RS > 70) 4. Former-leader gate (most important): ran 100%+ from a prior trough into its peak over the last 1–3 years, and the peak is at least ~5 weeks old (O'Neil: best shorts are 5–15 weeks after the top, not at the peak). 5. Distribution volume: down-days heavier than up-days over 50 sessions (up/down-volume ratio at or below 0.85 — the inverse of accumulation). 6. Decelerating fundamentals: EPS momentum not accelerating AND (EPS SMA turning down OR a recent earnings miss) — deceleration/disappointment, not absolute badness. 7. Liquidity floor: enough average daily dollar volume to borrow and exit. 8. A ticker is reported only if it passes EVERY technical AND fundamental gate. Output includes the symbol, sector, sub-sector, RS, all Stage-4 technical flags, former-leader/timing metrics (prior-advance %, % below the high, peak age, distance to the declining 50-day = overhead resistance), volume/liquidity, and the deceleration fundamental flags. Squeeze risk (high short interest / days-to-cover) and the exact rally-into-resistance entry are assessed downstream by the AI analysis pass.
Where the "smart money" is trading. Aggregates recently disclosed SEC Form 4 insider trades (executives & directors) and STOCK Act disclosures from the Senate & House, then ranks tickers by how significant the activity is — distinct buyers (a 3+ buyer cluster is the headline signal), dollar size, and recency. Shows net buy/sell tilt with C-level, director and Congress flags. Open-market trades only (option exercises, grants and gifts are filtered out).
Every NYSE & NASDAQ stock that IPO'd in the last year, run through the same momentum + growth-fundamentals screen as AI Supercycle — trend template (50/150/200-day SMA alignment, slope, 52-week proximity, relative strength) plus increasing EPS and three straight earnings beats. The whole IPO board is shown, ranked by RS, with per-row gate flags. Runs daily before the open.
Momentum + fundamentals across the AI buildout — GPUs, AI memory, semicap, optics, data-center power, and the hyperscalers spending the capex. Ranked by relative strength, flagged for which names clear both gates.
Proprietary stock screen developed by newsimpactscreener. The NASDAQ and NYSE companies that pass every Buffett-style quality gate: 10y avg ROE ≥ 15%, ROIC ≥ 12%, free cash flow positive in 8+ of last 10 years, FCF/Net-Income ≥ 0.8, net-debt/EBITDA ≤ 1.5, no dilution over 5y, 10y EPS CAGR ≥ 7%. Excludes financials, REITs, and utilities (different accounting). Updates quarterly after each earnings season.
Proprietary stock screen developed by newsimpactscreener. Combines a multi-stage technical filter with a growth-fundamentals overlay across the entire NYSE + NASDAQ universe. Pipeline: 1. Universe: all listed NYSE + NASDAQ tickers. 2. Pre-screen: actively traded AND relative-strength rating > 80. 3. Trend template — all conditions required: • close > SMA50 > SMA150 > SMA200 • SMA200 rising (20-day slope confirmation) • close within 25% of the 52-week high • close at least 25% above the 52-week low • RS > 70 4. Growth fundamentals overlay — both conditions required: • EPS direction (SMA) is increasing • Earnings beat estimate in each of the last 3 quarters 5. A ticker is reported only if it passes EVERY technical AND fundamental gate. Output includes the symbol, sector, sub-sector, RS rank, all technical flags, supplementary metrics (ADR%, volume ratio, accumulation, buy-range proximity, RS-line new high), and the two fundamental flags. Lower RS rank = higher percentile.
Dummy screening that returns AAPL every run — used to verify the subscription, fan-out, and Telegram flow.
Stage 2 screen: price > MA50 > MA150 > MA200, 200-day MA rising, near 52-week high.
Choose which screenings to follow. Delivered on schedule.
