Meta Force Space
BTC $63,178.00 -1.52% ETH $1,764.35 -0.86% SOL $73.42 +1.59% XRP $0.9762 +1.83% BNB $582.97 -0.71% DOGE $0.0586 +0.40%
← Back to the news

Bitcoin power-law models predict a rebound without real proof

Quick Take

  1. A November preprint leaves Bitcoin's return toward its power-law trend unresolved, while its own forecasts assume that behavior.
  2. The study's slowing-growth finding disappears when its test allows shocks to persist beyond a random walk.
  3. Its 2027-2030 forecasts will test predictive performance, while the authors warn their uncertainty intervals are probably too narrow.

The power-law model links Bitcoin's price to its age, but the recovery forecasts in a Nov. 10 preprint also assume that departures from the long-run curve reverse, a tendency its historical analysis leaves unresolved.

Authors Carlos Baquero and Raquel Menezes argued that Bitcoin's long-run growth rate has slowed under the conditions their test allows.

The study's price record ends on Sept. 19, so its results do not explain November's selling.

Model advocate Stephen Perrenod made the attractor argument explicit in a June 5 analysis, arguing that tests of price deviations supported an attractor around which bubbles and bear markets occur.

He also cautioned that those tests did not predict next month's price or prove the relationship must continue indefinitely.

Reports on power-law likewise described an attractor framework while leaving the force sustaining it unsettled.

Baquero and Menezes used 820 weekly observations from January 2011 through September 2026. Within a declared family of possible price deviations, their test found evidence of a slowing long-run growth rate.

It rejected constant drift in expected log price at a nominal 5% significance level, compatible with a power-law trend, but does not identify it uniquely.

Their main family allowed shocks to persist as much as a random walk, where a shock need never fade. When a prespecified sensitivity check allowed even more persistent changes, the rejection disappeared, showing how the conclusion depended on the persistence assumption.

The paper also found that a Gompertz curve, which approaches a ceiling, described the historical record almost as well as the power law.

The recovery is built into the forecast

The authors said the fitted models for price deviations revert toward their trends, so most forecasts anticipate a rise from the approximately $81,000 September endpoint.

The restoring tendency entered through the chosen models even though the historical analysis cannot establish it within the evaluated approach.

For Dec. 28, 2030, the power-law model produced a $383,000 median and a 90% interval of $150,000 to $1,015,000. Across all five trend models, the medians ranged from $85,000 to $1,011,000.

The authors warned that their predictive intervals are probably too narrow and are not calibrated. Each forecast combines the fitted distribution with simulated and refitted alternatives, but the refits explore only neighboring choices for how deviations behave.

That leaves broader uncertainty about persistence only partly represented.

The result is a model that assumes a pull toward trend and cannot use its projected rebound as evidence that the pull exists.

Where a rebound enters the model

The study separates the historical trend question from the reversion its forecasts assume. Compare the two parts of the reasoning.

Where does the restoring tendency enter?

The slowdown finding holds within the declared shock family; allowing more persistent changes removes it. Reversion remains unresolved.

A forecast that assumes a pull toward trend cannot establish that pull through its projected rebound.

The paper's historical conclusion depends on its persistence family. Reversion remains unresolved within the evaluated models and six-feature method. Diagrams show reasoning, not measured causal forces or guaranteed price paths.

Sources and evidence

Sources

  1. Baquero and Menezes, November 10 preprint

Supporting facts

  • Reported statement The November 10 arXiv preprint by Carlos Baquero and Raquel Menezes distinguishes the shape of Bitcoin's expected log-price trend from whether price deviations revert to it. [1]
  • Reported statement At a nominal 5% level within its declared family, which permits shocks as persistent as a random walk, the study rejects constant drift in expected log price in the direction of slowing trend growth; this does not identify the power law uniquely. [1]
  • Reported statement A prespecified sensitivity analysis extending fractional persistence to 1.4, beyond a random walk, removes the rejection of constant drift; this shows assumption sensitivity rather than proving that Bitcoin has such persistent deviations. [1]
  • Reported statement The paper leaves mean reversion unresolved. Its low detection-power bounds concern six low-frequency features and the evaluated deviation models, not every possible method applied to the full price series. [1]
  • Reported statement The paper says its fitted forecast deviation models revert toward their trends, so most forecasts expect a rise from the roughly $81,000 September endpoint. The restoring tendency is a model assumption that its historical analysis cannot establish. [1]
  • Reported statement The paper fixes forecast evaluation at the last Saturday of 2027, 2028, 2029 and 2030 using a joint log-density score; better scores would show better prediction of those four prices, not prove a generating law. [1]

Method

Conceptual dependency diagrams, not price charts. The historical view separates the conditional slowdown result from unresolved reversion; the forecast view shows the fitted trend and assumed reversion feeding a projected rise. No numerical extrapolation or arithmetic.

Scope

The paper's historical conclusion depends on its persistence family. Reversion remains unresolved within the evaluated models and six-feature method. Diagrams show reasoning, not measured causal forces or guaranteed price paths.

Infographic by CryptoSlate

The paper describes itself as a preregistered reanalysis of a record the authors had already studied. They reported freezing the protocol and posting its hash on Oct. 6, applying the historical test once on Oct. 7, then registering the results and forecasts later that morning.

Those forecasts target the last Saturday of each year from 2027 through 2030 and will be assessed jointly using a log-density score, which measures how well the predicted distributions match the eventual prices.

Better performance would demonstrate better prediction of those four observations. The distinction remains consequential for a Bitcoin recovery case: a historical growth curve can frame a forecast, but an assumed return toward it is still a proposition for future prices to test.

Editorial credits

Liam 'Akiba' Wright
Liam 'Akiba' Wright
Editor-in-Chief CryptoSlate

Also known as "Akiba," Liam Wright is a reporter, podcast producer, and Editor-in-Chief at CryptoSlate. He believes that decentralized technology has the potential to make…

Gino Matos
Gino Matos
Reporter CryptoSlate

Gino Matos is a law school graduate and a seasoned journalist with six years of experience in the crypto industry. His expertise primarily focuses on the Brazilian blockchain…

Originally published by CryptoSlate on

Read the original on CryptoSlate ↗

Text and images are the property of CryptoSlate and are reproduced here with attribution and a link to the original publication.

More stories

All the latest news