H-021: ETH out of the market when 7-day net deposits to exchanges are in their top 20%
Weak Family: flows · Status: weak
Do Ethereum exchange inflows predict price drops? The idea did a bit better than simply buying and holding, but not by enough to rule out luck. Treat it as unproven.
Result
oos: wins 0/1 (need 1), beats buy-and-hold 1/1
| Asset | Period | Sharpe | Hold Sharpe | CAGR | Hold CAGR | Max drawdown | Hold drawdown | In market | p-value | Beats hold | Counts as win |
|---|---|---|---|---|---|---|---|---|---|---|---|
| ETHUSDT | oos (2022-01-01 → 2026-10-13) | 0.40 | 0.22 | +6.6% | -7.8% | -78.6% | -74.0% | 80% | 0.082 | yes | no |
Equity curves
Growth of 1 unit, log scale, fees included. Only days on which the rule is fully defined are counted.
The same rule on every coin
Exploratory check of this rule on all coins since 2022-01-01. It is not part of the verdict above.
- ✓works (passed the chance check)
- ↑better than holding, could be luck
- ✗worse than holding
- ·not enough data
- original coin of the hypothesis
| Coin | ✓ | Result | Sharpe: rule / holding | CAGR | From |
|---|---|---|---|---|---|
| BTC | ↑ | better than holding, could be luck | 0.51 / 0.48 | +13% / +12% | 2022-01-01 |
| ETH | ↑ | better than holding, could be luck | 0.39 / 0.20 | +6% / -9% | 2022-01-01 |
| SOL | ✗ | worse than holding | 0.29 / 0.35 | -9% / -10% | 2022-01-01 |
| BNB | ✗ | worse than holding | 0.38 / 0.42 | +7% / +8% | 2022-01-01 |
| XRP | ✗ | worse than holding | 0.26 / 0.51 | -5% / +10% | 2022-01-01 |
| ADA | ✗ | worse than holding | -0.18 / -0.01 | -31% / -32% | 2022-01-01 |
| LTC | ✗ | worse than holding | 0.06 / 0.11 | -14% / -18% | 2022-01-01 |
| LINK | ✗ | worse than holding | 0.08 / 0.30 | -18% / -10% | 2022-01-01 |
| DOGE | ✗ | worse than holding | 0.18 / 0.26 | -14% / -15% | 2022-01-01 |
| XLM | ✗ | worse than holding | -0.01 / 0.30 | -22% / -9% | 2022-01-01 |
| TRX | ↑ | better than holding, could be luck | 0.77 / 0.74 | +26% / +36% | 2022-01-01 |
| EVER | ↑ | better than holding, could be luck | -0.10 / -0.15 | -54% / -68% | 2022-03-19 |
| GRAM | ✗ | worse than holding | -0.31 / 0.13 | -32% / -17% | 2023-03-14 |
Why it might work
Same as H-020 for Ethereum, an independent asset with its own exchange flows. Alpha 0.025 each (Bonferroni for the pair). Spec revised on 2026-10-14 before any test was run (full history available).
Verdict history
- 2026-10-14: Weak (this engine, data to 2026-10-13)
Pre-registered specification
kind: timing_rule
rule:
type: feature_vs_rolling_quantile
feature: exnetflow_eth_7d
q: 0.8
long_when: not_above
lookback: 365
min_periods: 180
lag: 1
mode: long_flat
fee: 0.001
universe:
- ETHUSDT
periods:
- name: oos
start: '2022-01-01'
significance:
method: circular_shift
n: 2000
alpha: 0.025
criterion:
min_wins:
oos: 1
require_significance: true