EquationDB

Abnormal activity & anomalies

For surveillance and compliance teams, risk managers, quants, event-driven PMs

Find what is unusual today, not what is merely big: statistically rare moves, volume without price, price without volume, volatility regime breaks, unusual insider buying and accounting red flags, each measured against the symbol's own history.

  • Financial markets
  • 13 steps
  • Runs on live data

How EquationDB answers it

Each step is one query on live data. Run them in order, or open any one and adapt it: change the symbol, the station, the dates or the filter.

  1. The rarest events of the day

    Rarity is a percentile against each symbol's own past, so a 3% move in a utility can rank above a 6% move in a biotech.

    EVENTS * IN top500 LAST 1d WHERE rarity >= 98 SORT rarity DESC
    Try it →
  2. Volume shocks this week

    Magnitude is volume as a multiple of normal. Shocks without news are the first thing a surveillance desk looks at.

    EVENTS volume_extreme, volume_surge IN top500 LAST 5d SORT magnitude DESC LIMIT 20
    Try it →
  3. Heavy volume, flat price

    Three times normal volume while the price barely moves: block trades, index events or quiet accumulation or distribution.

    GET top500 SELECT symbol, sector, ret, rvol(20) AS rv WHERE rvol(20) > 3 AND abs(ret) < 1 SORT rv DESC
    Try it →
  4. Big move on light volume

    A 5% move that nobody traded is fragile: often gap-and-fade or thin-liquidity marking.

    GET top500 SELECT symbol, sector, ret, rvol(20) AS rv WHERE abs(ret) > 5 AND rvol(20) < 1 SORT ret DESC
    Try it →
  5. Volume at a one-year extreme

    Today's volume ranked against the past year of the same stock.

    GET top500 SELECT symbol, sector, close, ret, pct_rank(volume, 252) AS vol_pctile WHERE pct_rank(volume, 252) >= 99 SORT vol_pctile DESC
    Try it →
  6. Volatility regime break

    Realized volatility over the last month is more than 1.5 times its one-year level: something changed in the name.

    GET top500 SELECT symbol, sector, rv_cc(20) AS vol_20d, rv_cc(250) AS vol_1y WHERE rv_cc(20) > 1.5 * rv_cc(250) SORT vol_20d DESC
    Try it →
  7. Extreme gaps

    Opening gaps that are rare for the stock: overnight information the market had to reprice.

    EVENTS gap_up, gap_down IN top500 LAST 5d WHERE rarity >= 95 SORT rarity DESC
    Try it →
  8. Beta regime shifts

    The stock stopped moving with the market the way it used to: a changed story, a deal, or a crowded position unwinding.

    EVENTS beta_shift IN top500 LAST 1mo SORT magnitude
    Try it →
  9. Anomalous days in one name

    Every day in the last year with an extreme return, range or volume z-score, labelled by type.

    ANALYZE anomalies TSLA
    Try it →
  10. Unusual insider buying

    Open-market purchases by insiders and 10% owners. Buying is rarer and more informative than selling.

    INSIDERS IN top500 LAST 1mo WHERE type LIKE 'P%' SORT value DESC LIMIT 20
    Try it →
  11. Receivables outrunning sales

    A classic accounting red flag: revenue booked but not collected (channel stuffing, aggressive recognition).

    FINANCIALS IN top500 WHERE period <> 'FY' AND sector <> 'Financial Services' AND receivables_yoy - revenue_yoy > 25 AND revenue_yoy > 0 SELECT period_end, revenue_yoy, receivables_yoy, dso SORT receivables_yoy DESC LIMIT 20
    Try it →
  12. Inventory piling up

    Inventory growing far faster than sales often precedes write-downs or margin pressure, unless it is a deliberate build.

    FINANCIALS IN top500 WHERE period <> 'FY' AND inventory_yoy - revenue_yoy > 30 AND revenue_yoy > 0 SELECT period_end, revenue_yoy, inventory_yoy SORT inventory_yoy DESC LIMIT 20
    Try it →
  13. Profits without cash

    Reported a profit but burned operating cash in the same quarter: the earnings are accruals, not cash.

    FINANCIALS IN top500 WHERE period <> 'FY' AND net_income > 0 AND operating_cf < 0 SELECT period_end, net_income, operating_cf, accruals SORT accruals DESC
    Try it →

Run it on your own question

Sign in and press Try it on any step, or ask for a short demo on your data.

Request a trial

More financial markets use cases