Skip to main content
Once a day Shumi is asked one fixed question about one coin, and its answer is published here unedited. Every take is published, including takes that came back stale, unparsed or with an error. An outcome is a new block added below the entry it belongs to. Status: registered, unresolved. The record runs on version 2 of its rules, registered on 2026-10-29, from day one on 2026-10-31. It stays “registered, unresolved” until its first reading. Version 1. Entries before 2026-10-31 ran on version 1, which required each entry to be live by 00:00 UTC the next day. The entries for 2026-10-16, 10-17 and 10-18 went live on 2026-10-21. The entry for 2026-10-23 went live on 2026-10-24, and those for 2026-10-25, 10-26 and 10-27 on 2026-10-28. 2026-10-19, 10-20 and 10-21 have no entry. Version 1 entries stay published as they are and are not scored. Their “version 1” links open version 2; version 1 itself is here.

How a coin is picked

At 12:15 UTC a query counts how often each coin appeared in Shumi’s hourly sentiment summaries over the previous 24 hours and picks the highest count. Ties go to the larger market cap. Eligible coins are the top 500 by market cap, excluding stablecoins, wrapped, bridged and liquid-staking tokens, real-world-asset rows (stocks, commodities), coins without a current trend, coins picked in the previous 7 days, and coins with a plan here still open. Every entry lists the five highest counts next to the pick.

The question

At 13:15 UTC the same message is sent once in a new Shumi chat, with no follow-up and no regenerating. It asks which plan the data favours today: long, short or neither. Shumi states both plans with entry zone, stop, target and data score, the exit rule, the biggest risk, the venue, and the time of every input it used.

How a plan is scored

  • A plan fills only when price reaches its entry zone. A plan that never fills is published with the reason it lapsed and is not scored.
  • A filled plan ends at the first of: a daily close beyond its stop, the site’s trend turning against it, or a reversal signal once the plan is at least 3 % in profit. Reaching the printed target leaves the plan open. There is no time limit.
  • Results are in R (the loss the plan stated up front) and in account terms at 1 % risk per plan, long or short, after costs of 0.4 % round trip for coins ranked 1 to 100 and 1 % for ranks 101 to 500. Funding over the hold is shown as a signed rate.
  • NEITHER is a full answer. It is scored as staying out.

The bar

The record is read twice: first when 30 plans have resolved that were entered in at least 8 different weeks, then at 60 plans entered in at least 12 different weeks. A reading is published as “passed” or “not passed”. It passes only if all of these hold after costs:
  1. The average result per plan is above zero, and so is the average of weekly averages (each week of entries counted once).
  2. Across every published day, Shumi’s total is ahead of taking the published long plan every day on the same coin.
  3. At least 40 % of the plans end with a net result above zero.
  4. No scheduled day is missing from the record.

Entries

Each entry shows when the question was asked and when the answer was published, the coin and why it was picked, and the site trend at selection. It lists any labels (stale input, exit line missing, no plan, unparsed, error, no eligible coin), both plans as parsed, Shumi’s full answer verbatim and the link to the live Shumi session.

R-2026-10-16

Full take, verbatim:
Published at 2026-10-21T07:40:26Z.

R-2026-10-17

Full take, verbatim:
Published at 2026-10-21T07:51:50Z.

R-2026-10-18

Full take, verbatim:
Published at 2026-10-21T08:12:55Z.

R-2026-10-22

Full take, verbatim:

R-2026-10-23

Full take, verbatim:

R-2026-10-24

Full take, verbatim:

R-2026-10-25

Full take, verbatim:

R-2026-10-26

Full take, verbatim:

R-2026-10-27

Full take, verbatim:

R-2026-10-28

Full take, verbatim:

R-2026-10-29

Full take, verbatim:

R-2026-10-30

Full take, verbatim:

R-2026-10-31

Full take, verbatim:

R-2026-11-01

Full take, verbatim:

R-2026-11-02

Full take, verbatim:

R-2026-11-03

Full take, verbatim:

R-2026-11-04

Full take, verbatim:

R-2026-11-05

Full take, verbatim: