Memecoins on Solana
Trade Desk: a bot that scouts brand-new Solana coins, screens them with Solana Pulse safety checks, and paper-trades them with different exit rules.
What we tested
| Test | Data | Result |
|---|---|---|
| 6 live paper lanes, $1,000 each | Main, Fast, Ladder A/B, WAIT-5 momentum, wallet copy | All 6 lost: 641 trades, −$720 since the Nov 7 reset |
| Every paper run, Nov 1–15 | 16 runs across all lanes; Ladder A kept running after the others were retired Nov 9 | 0 of 16 ended in profit: 2,639 trades, 909 wins (34%), −$2,665. Ladder A alone since Nov 9: 986 trades, −$581 |
| Strict replay, every exit rule | 16,071 coins with 1-minute candles (Nov 1–4) | Every exit loses: typical trade −11.6% to −17.9% |
| 120-cell exit grid | Take-profit 10–100% × stop 6–40% × 30–600 min, trailing stops | No lead |
| Entry filters | Safety verdict, liquidity, volume, buy/sell ratio, pool age | Safer coins stop the rugs but still bleed ~2% a trade to costs |
| 6 brand-new strategies (Claude + Gemini) | Dip buys, breakouts, second-wave, capitulation bounce, flow; 5,705 coins at 1%/side | 0 leads; big samples −5% to −19% a trade |
| Copy the "smart wallets" | 100 coins, 105,857 transactions, every wallet's profit | Failed: early winners lost on later coins (−12.6 SOL) |
Who actually makes money on a new coin
From the wallet study (one row = one wallet trading one coin, inside the first 2 hours):
| Who | Wallets | Profitable | Total |
|---|---|---|---|
| Sold more than they bought (got tokens before trading opened) | 2,828 | 95.8% | +1,816 SOL |
| Pool creators | 49 | 59.2% | +124 SOL |
| Bought in the launch slot | 167 | 34.7% | −187 SOL |
| First buy within 10 s | 1,685 | 18.7% | −584 SOL |
| First buy 10–60 s | 8,033 | 4.1% | −6,417 SOL |
| First buy 1–10 min | 18,410 | 1.1% | −1,709 SOL |
| First buy after 10 min | 382 | 0.5% | −31 SOL |
What we found out
full write-upraw data + scripts23,379 coins of candleslive paper desk
Crypto: established Solana tokens
Not new launches: timing rules on established tokens (SOL, JUP, BONK, WIF), plus a check of whether safety ratings match what happened next.
What we tested
| Test | Data | Result |
|---|---|---|
| 436 timing rules (109 per token) | ~7 months of hourly price + volume, each token's main Solana pool (GeckoTerminal). Rules found on the first 60%, judged on the last 40%. Costs 0.1–0.3% a side | 0 beat holding in both periods (random rules: 2) |
| Rule families | Moving-average crosses, price above average, Bollinger bounce and breakout, RSI, breakouts, momentum, volume spikes, hour of day, day of week, dip buys in uptrends | 25 made money in both periods. All 25 trailed holding, because the test period rose 19–35% on every token |
| Luck check vs random timing | The same number of trades at random times, many runs | 3 beat random in both periods. They are candidates for a forward test, not edges, because they were picked from 436 |
The 3 candidates (not proven): forward test, Nov 1–15
Same code and costs, run on the 14 days of prices that came after the study. Only 2–6 trades each, far too few to call an edge.
| Rule | Train | Test | Random did as well | Forward (vs holding) |
|---|---|---|---|---|
| JUP: in an uptrend (above 168-h average), buy below the lower Bollinger band, sell at the middle band or after 48 h | +11.0% | +31.1% | 9% / 1% | +3.2% vs +4.3%, 3 trades |
| JUP: after an hour with 5× normal volume and price up, hold 24 h | +13.9% | +40.7% | 15% / 2% | +10.0% vs +4.3%, 2 trades |
| WIF: buy below the lower Bollinger band (20, 2.5), sell at the middle band or after 72 h | +6.8% | +15.9% | 4% / 8% | −1.5% vs −25.2%, 6 trades |
What we found out
Regular stocks (US ETFs)
Night Desk: an overnight desk that searches for stock rules and paper-trades only the ones that beat holding the S&P 500 (SPY) after costs.
What we tested
| Round | Rules | Result |
|---|---|---|
| 1 | 20-day momentum + breakout, 60-day momentum above the 50-day average, pullbacks in an uptrend. Walk-forward test with the newest 40% unseen | Best +10% vs SPY +30% |
| 2 (AI search, 27 rules) | 200-day trend filters, sector rotation, panic dip-buying, volatility timing. Searched on Jul 2020 → Nov 2025; the newest year was never written to disk | Finalists beat SPY on search data (+67.6% vs +61.5%), then lost on the locked year |
| Live paper desk (Alpaca, Nov 9–15) | The desk places only tiny "unproven" $50 probes until a rule passes; it found 2 (LLY Nov 9, COST Nov 13) | +$1.81 open on $100 of probes. Far too small to mean anything; no rule has passed yet |
The locked year (Nov 2025 → Nov 2026), tested once
| Strategy | Return | Max drawdown |
|---|---|---|
| Just hold SPY | +12.9% | 8.9% |
| Trend + panic dip (20/200) | +4.9% | 8.9% |
| Trend only | +4.7% | 8.9% |
| Trend + panic dip (15/200) | +4.0% | 8.9% |
What we found out
Alpaca daily bars, 13 ETFs (SPY, QQQ + 11 sectors), Jul 2020 → Nov 2026, 5 bps a side · full write-upevery rule triedprice data
Forex
It started with an old tip: "a 5/16 moving-average crossover with Japanese candlesticks on EUR/USD is profitable." We tested that, everything people usually add to it, and then effects from published research.
Indicator systems (~1,500 versions)
| Tested | Result |
|---|---|
| 5/16 SMA + EMA crossover, daily 1999–2026 | Made a little before 2015, lost since (−2 to −3%/yr) |
| Same on 15m / 1h / 4h / daily + candle patterns | 15m and 1h lose everywhere (15m: −19,795 pips 2016–21). 4h + engulfing was the only positive one |
| EMA ribbon 5/16/35/68 with volatility gates | 0 of 45 combinations positive in all 3 periods |
| "Everything" system + 1,260 stop/trail/target settings | 4h: ~70–76% of settings positive on EUR/USD. 1h and 15m: 0 of 1,260 |
| Self-tuning version that "learns as it goes" | Chased last period's winner and did not beat a fixed setting |
| No stop, take-profit only | Showed "100% wins" while holding losers up to 5½ years at −2,000 pips. A trap |
| Hidden-data test (saved to git before it ran) | Best 4h system, unchanged: −61.9R on 9 other pairs (515 trades), −630 pips on EUR/USD 2005–2015 |
Effects from published papers (rules fixed from the papers before running)
| Effect | Result |
|---|---|
| Fed day: sell USD from 5 PM New York the evening before a scheduled Fed announcement until 5 PM on the day Mueller, Tahbaz-Salehi & Vedolin, Journal of Finance 2017 | Holds. EUR/USD 2005–2026: 174 events, +2,717 pips, t = 2.3; also positive on GBP, JPY and AUD. The same trade on other days: −2 to −3 pips. Last 12 months negative. |
| Month-end rebalancing into the London 4 PM fix Melvin & Prins 2015 | Fails: EUR/USD −1,911 pips |
| A currency weakens during its own trading hours Breedon & Ranaldo 2013 | Real but not tradeable: +2.25 pips/day before costs (t = 4.8); the 1.5-pip spread eats it |
What we found out
Oanda candles (15m → daily, 10 pairs, measured spreads, back to 2005), FRED, federalreserve.gov · full write-upfindingsevery price file
How we tested, and why most backtests lie
Our biggest early "wins" (+2,000% a trade, a 6,526× coin, Sharpe ratios above 3) were all bugs in the test, not edges in the market. These rules are how we caught them.
- Real data, named. Every price has a named source. Missing data is "unknown", never filled in.
- No look-ahead. A signal on a candle's close fills at the next candle's open. If a stop and a target hit in the same candle, the stop counts first.
- Real costs. Measured spreads per currency pair, 5 bps a side for ETFs, 1% a side and −100% write-offs for dead memecoins.
- Several periods, not one total. A rule has to make money in each period, not just overall.
- Locked data. The newest stock year was never written to disk during the search, and the script refuses a second run. Forex kept 9 other pairs and 2005–2015 hidden.
- Save the test before running it. Hidden-data tests were committed to git first, so nobody could adjust them after seeing results.
- Count the tries. Adjust confidence for how many rules were tested. For settings grids, report how much of the grid works, not the best cell.
- Compare with doing nothing clever. Stocks vs holding SPY, crypto vs holding the token, rules vs random timing.
- Then forward-test. The future is the only data none of these systems has seen.