Predict the next 5 trading days' moves of 9 Nasdaq stocks

$250 reward. Entries closed . Racing live. What to build: Write a program that reads the on-chain price history of 9 tokenized Nasdaq stocks (xStocks on Solana) and forecasts, for each of the 5 trading days after entries close (2026-11-10 to 2026-11-16), the order of the 9 by that day's return, a probability for each stock at each place, and each stock's return in half-point bins, for the highest log score over those days: 1st place is the best forecast, and a forecast must also beat our house forecasts to take any place. Reward bar: A reward needs a score better than the best house entry's. An entry that does not beat it keeps its spot in the ranking but earns no reward. Each bounty's rules give the exact bar.

This bounty's rewards are paid in USDC on Solana from make.fun's reward wallet, with no escrow.

Rewards

$250 · 20 places paid

  • 1st $50
  • 2nd $35
  • 3rd $25
  • 4th–10th $10 each
  • 11th–20th $7 each

Full brief

Nine big Nasdaq stocks trade on Solana as xStocks, tokens that track their shares around the clock. We want a forecaster that reads their recent prices and says, with honest probabilities, how the nine will rank by return on each of the next five trading days, and how far each will move.

Context

Your entry is a program that reads hourly price bars of the nine tokens, recorded on chain by the house, and writes one forecast: for each of the 5 trading days after entries close, a probability for each stock at each place of that day's order by return, its guess at that order, and a probability for each stock's return in half-point bins from -10% to +10%. It runs offline in the sandbox, with no network: everything it knows is in the history it is given, and nothing calls a model.

Entries are open for 49 hours, from 2026-11-08 01:00 UTC to the deadline, 2026-11-10 02:00 UTC. Before the deadline every entry is scored on a small practice forecast from an earlier recording, and its score shows as it lands. After the deadline the house records the 5 trading days from 2026-11-10 to 2026-11-16, takes each stock's close as the average of its on-chain price over the 30 minutes before the market closes, and every final entry runs once more on the whole history up to 2026-11-09 23:00 UTC, three hours before the deadline, the same for every entry and the house, and is scored on each of those days.

The score is the log score: on each day, the natural log of the probability you gave the stock actually at each place and the bin each stock's return actually fell in, added up over the places, the stocks and the days, so confident right calls score close to 0 and confident wrong ones far below. Ties are broken by how well your guessed orders match the real ones. A prize needs a higher score than the best house entry: the house baseline, which expects no stock to beat another, and a forecast by a house AI model when the house enters one. Once the organisers have attached the closes the house recorded, everything runs by itself, with no further admin step unless a check holds it, and each winner is paid automatically to a Solana wallet linked to their account by signature.

Deliverables

  • A public GitHub repository owned by your own GitHub account, created after the competition opens, under an OSI-approved license, with main.ts (Node 22) or main.py (Python 3.13) in the repository root that writes /output/forecast.json
  • The AI coding-agent transcripts of the sessions that built it (Claude Code, Codex, Cursor and others), uploaded with each submission

Requirements

  • Standard library plus source you vendor into the repository: nothing is installed before the program runs, and it has no network
  • Read the history in /input; two runs on the same history must write the same forecast
  • At most 300 seconds, 1 CPU and 1024 MB per run
  • At most 5 submissions a day and 20 in all; your last submission before the deadline is your final entry