Real-World & Alternative DataExtended setexperimental liveNew

Port Ship Count Throughput

Updated 5-day (sentinel-2 revisit)Data needs: highlong only

2018

Donaldson-Hornbeck 2016 (trade infrastructure) + Brooks-Sandeep 2018 (satellite-derived shipping as leading indicator). Sentinel-2 ESA free-tier specialization.

Citation only, paper link pending.

In plain terms

We count ships at major container ports from free satellite imagery; spikes signal a global trade-throughput pulse that propagates to shipping and consumer names.

How it works

Sentinel-2 imagery at 10m over 8 major container ports (LA/LB, Rotterdam, Antwerp, Hamburg, Felixstowe, Le Havre, Algeciras, Valencia) detects ships via a brightness-threshold heuristic over NDWI water masks. Daily global ship count z-scored over 252d; spikes broadcast as a global trade-throughput signal. Substrate gates surface logistics/shipping/consumer-discretionary names that actually react. Complementary to baltic_dry_ais_proxy (AIS catches broadcasting ships; Sentinel-2 catches dark ships).

Live results

0 times picked on its own · 90 times inside a blend (73 beat the stock) · updated 2026-07-06

This strategy is a frequent ingredient in blends that combine a few strategies on one stock. It has contributed to 90 such blended picks (73 of which beat simply holding the stock). Picking it on its own is only one of the ways it shows up.

How its picks scored vs. buy & hold

Each pick is graded on a recent year it was never tuned on, against simply owning the same stock

Where its edge concentrates

Share of picks in each company-size group that beat buy & hold

How often it trades

Active vs. patient. Bars on the left mean it waits for rare setups; bars on the right mean it trades often

Return vs. buy & hold

How much each pick beat or trailed simply owning the stock over the test year (extreme microcap moves trimmed)

Loading substrate evidence…

Data dependencies

Daily prices
Adjusted-close OHLCV for every US-listed ticker; primary price feed.
Sentinel2 port panels
A data feed this strategy reads, refreshed on its normal schedule.

Expected edge

Reported return: 1-3%/yr
Tested over: 2015-present (Sentinel-2 launch)

1-3%/yr on logistics + consumer-discretionary cross-section.

Example tickers where this is likely to fire

FDX UPS CHRW EXPD MATX KEX ZIM MAERSK.CO

Illustrative only, the signal fires based on the live data, not a fixed list.

Related families

Baltic Dry Ais ProxyReal-World & Alternative Data

NOAA AIS shows dry-bulk shipping accelerate → shippers + miners rally 1-2 months.

Port Container La Signal MvpReal-World & Alternative Data

Internal heuristic: when LA port inbound-container throughput slows vs its ~1yr trend, big importers tend to underperform; when it accelerates, rails/logistics tend to rally. Not validated against an academic paper.

Explore Port Ship Count Throughput on alphactor.ai

See which tickers this family is currently firing on, with live signals and rankings.

Open universe with this filter →Browse all 572 families