📊 Full opportunity report: Week Three — Foundation model vs Brownian motion. Kronos on five-minute BTC. on ThorstenMeyerAI.com — validation score, market gap, and execution plan.

TL;DR

A recent test comparing the Kronos foundation model to a Brownian motion baseline for 5-minute Bitcoin trading found no statistically significant advantage. The experiment aimed to determine if modern learned models outperform traditional stochastic assumptions.

Recent testing of the Kronos foundation model against a Brownian motion baseline for 5-minute Bitcoin trading shows no statistically significant advantage for the model in out-of-sample data.

Over two weeks, a researcher compared Kronos, a large open-source foundation model trained on global exchange data, with a traditional geometric Brownian motion model in a simulated trading environment. The test involved 497 BTC trades, reconstructing market context for each, and evaluating model predictions against actual outcomes.

The results indicated that Kronos’s predictive accuracy, measured by Brier score and log-loss, was statistically indistinguishable from the Brownian baseline on out-of-sample data. Specifically, the difference in Brier scores was only 0.0011, well within the margin of noise for such tests. Consequently, Kronos did not outperform the simpler Brownian model in this scenario, leading to the conclusion that the modern foundation model does not currently provide a trading edge over traditional assumptions in this context.

Polybot Week 3 — Kronos vs Brownian — Thorsten Meyer AI

KRONOS

● RESEARCH SERIES / MAY 2026

THORSTEN MEYER AI · POLYBOT · WEEK 3

POLYBOT · WEEK 3

KRONOS vs BROWNIAN

Research Series · Foundation Model vs Classical Baseline · 2026-05-17

Foundation model
vs Brownian motion.
Kronos on five-minute BTC.

A modern learned model just lost to math from 1900. On 497 paired trades. Stage 2 is not happening.

Polybot’s fair-value strategy uses a 1900s geometric Brownian model to price 5-minute BTC outcomes. The natural follow-up after two weeks of negative parametric results: would a modern learned model trained on millions of real candles do better? The credible candidate: Kronos — open-source MIT-licensed foundation model, 25,000+ GitHub stars, AAAI 2026, four sizes from 4M to 499M parameters, trained on candles from 45 global exchanges. Test design: 497 paired (FILL→SETTLE) trades, Brownian baseline reconstructed line-for-line, Kronos-small (24.7M params) sampled with 16 forecast paths, scored on Brier + log-loss + hypothetical P&L, chronologically split for out-of-sample discipline. On 249 out-of-sample trades: Brownian 0.188 Brier vs Kronos 0.189 Brier. Gap 0.0011. Statistically indistinguishable. Stage 2 is not happening. But the paradox is more interesting than the verdict: when used as a directional signal Kronos fires 28% less often and wins 60.7% vs Brownian’s 49.1% — slightly better trader on hypothetical P&L, even while systematically over-confident in the tails (predicts 2.4% chance → actual 20.4% win; predicts 84% → actual 69.6%). The negative result is the answer. The methodology is what gets published.

Thorsten Meyer AI Polybot · Week 3 MIT-licensed · methodology public Research article · ~2,200 words Forezai · Polybot

This is not financial advice. Nothing in this article should be used to inform real trading decisions. The bot trades simulated money. If you build something like it and run it with real funds, the most likely outcome — by a wide margin — is that you lose those funds. That holds whether you use a Brownian model, a 100-million-parameter foundation model, or any other forecaster.

497

Paired (FILL→SETTLE) trades
all BTC · 5-min Up/Down markets

0.0011

Out-of-sample Brier-score gap
249 trades · statistically indistinguishable

2×

Kronos log-loss vs Brownian
signature of confident wrong predictions

+$538 / +$465

Hypothetical Kronos vs Brownian P&L
the paradox · 60.7% vs 49.1% win rates

POLYBOT WEEK 3· KRONOS-SMALL · 24.7M PARAMS· BROWNIAN BASELINE· 497 PAIRED TRADES · BTC· POLYMARKET 5-MIN UP/DOWN· BRIER 0.193 / 0.211 / 0.213· LOG-LOSS 0.567 / 0.604 / 1.080· OUT-OF-SAMPLE 0.188 vs 0.189· GAP 0.0011 · INDISTINGUISHABLE· STAGE 2 NOT HAPPENING· KRONOS BETTER TRADER · WORSE FORECASTER· 60.7% vs 49.1% WIN RATE· TAILS: 2.4% → 20.4% · 84% → 69.6%· POLYBOT MIT· KRONOS MIT· AAAI 2026 PAPER · 25K+ STARS· 11 MIN MAC M-SERIES · MPS BACKEND· 1,300 LINES OF PYTHON· RESEARCH_PIPELINE.MD PUBLIC· SAME GAUNTLET · DIFFERENT MODEL· POLYBOT WEEK 3· KRONOS-SMALL · 24.7M PARAMS· BROWNIAN BASELINE· 497 PAIRED TRADES · BTC· POLYMARKET 5-MIN UP/DOWN· BRIER 0.193 / 0.211 / 0.213· LOG-LOSS 0.567 / 0.604 / 1.080· OUT-OF-SAMPLE 0.188 vs 0.189· GAP 0.0011 · INDISTINGUISHABLE· STAGE 2 NOT HAPPENING· KRONOS BETTER TRADER · WORSE FORECASTER· 60.7% vs 49.1% WIN RATE· TAILS: 2.4% → 20.4% · 84% → 69.6%· POLYBOT MIT· KRONOS MIT· AAAI 2026 PAPER · 25K+ STARS· 11 MIN MAC M-SERIES · MPS BACKEND· 1,300 LINES OF PYTHON· RESEARCH_PIPELINE.MD PUBLIC· SAME GAUNTLET · DIFFERENT MODEL·

FIG. 01 — THE TEST PIPELINE

Five steps · for every paired (FILL → SETTLE) trade in the running session

~1,300 lines of Python · 11 minutes on Mac M-series with PyTorch MPS · methodology public, specific numbers local

Reconstruct OHLCV context of the 60 minutes leading up to fire-time. Pull from the bot’s local Binance recording where available; fall back to Binance’s public klines API otherwise. Cache to parquet so re-runs cost nothing.

Recompute the Brownian baseline in Python — a line-for-line port of the bot’s own fairValuePUp(spot, openPrice, secondsLeftFrac, windowVol) formula. Matches scipy.stats.norm.cdf to three decimal places.

Read off the market-implied probability from the FILL price — what Polymarket’s order book thought the side was worth at the moment of fire. The market’s view as a reference point.

Run Kronos-small (24.7M parameters) on the OHLCV context · sample 16 forecast paths to the window’s end · count the fraction in which the underlying closes above the open price. That fraction is Kronos’s predicted p(Up).

Record (p_brownian, p_market, p_kronos, actual_outcome, P&L). Score on Brier + log-loss + hypothetical P&L. Sort chronologically · split into first/second half · report on both halves separately.

The discipline that matters: if a model wins on the first half but ties or loses on the second, that’s the curve-fit-in-slow-motion pattern the previous two articles named, and it doesn’t count as edge. The whole pipeline is reproducible from docs/RESEARCH_PIPELINE.md. Any future candidate model gets a sibling directory in research//, reuses the same Brownian baseline, the same trade-log loader, the same OHLCV fetcher, the same metrics, the same out-of-sample split. Same gauntlet, different model, same discipline.

FIG. 02 — FULL-SAMPLE SCORING · 497 PAIRED TRADES

Three models · two probability-scoring metrics

Brier score and log-loss · the standard scoring rules for probability forecasts · lower is better

Model

Brier ↓

Log-loss ↓

BrownianGeometric Brownian motion · the 1900s baseline

0.193

0.567

Market-impliedPolymarket order book at FILL · reference

0.211

0.604

Kronos24.7M-param foundation model · 16 sampled forecast paths

0.213

1.080

Kronos’s log-loss is roughly twice Brownian’s — the signature of a model that makes confident, wrong predictions in the tails. Polymarket’s order book sits between the two, reasonably calibrated, slightly worse than the bot’s Brownian and slightly better than the foundation model. The 100-year-old math beat the 24.7M-parameter foundation model on both probability-scoring metrics.

FIG. 03 — OUT-OF-SAMPLE VERDICT · 249-TRADE TEST HALF

Chronologically-separated · never seen by tuning

The verdict the test was designed to deliver · noise band of repeated runs with different sampling seeds

Brownian · 249-trade test half

0.188

Brier score (out-of-sample)
lower is better

Kronos · 249-trade test half

0.189

Brier score (out-of-sample)
lower is better

The gap

0.0011

Statistically indistinguishable
inside the noise band

Kronos does not beat Brownian on a held-out chronologically-separated sample. So Stage 2 is not happening.

“Stage 2” was the planned next step: wiring Kronos into Polybot as a live strategy if Stage 1 produced a clear signal. The case is not earned by this data. For 5-minute BTC at the horizons the bot trades, the open Kronos-small checkpoint does not. Stop. The next candidate model — Chronos · TimesFM · Lag-Llama · a Kronos finetune on 5-min crypto · something else — goes through the same gauntlet. Most will fail it. That is the gauntlet doing its job.

FIG. 04 — THE PARADOX · BETTER TRADER vs WORSE FORECASTER

By operational standards Kronos wins · by probabilistic standards Kronos loses

The hypothetical-P&L counterfactual replays the same data through “what if Polybot fired on each model’s probability”

Operational view · Kronos as the better trader

Kronos fires less · wins more · nets slightly more.

Hypothetical fires

201

Brownian fires (reference)

279

Win rate (Kronos)

60.7%

Win rate (Brownian)

49.1%

Hypothetical net P&L (Kronos)

+$538

Hypothetical net P&L (Brownian)

+$465

Fires ~28% less often and wins more reliably when it does. If you use Kronos as a directional signal in a broader system that does its own sizing — closer to how TradingAgents uses analyst outputs — the directional accuracy might still be useful.

Probabilistic view · Kronos as the worse forecaster

Systematically over-confident in the tails.

Kronos predicts

2.4%

Trades actually win

20.4%

Kronos predicts

84%

Trades actually win

69.6%

Log-loss vs Brownian

~2× worse

Brier (full sample)

0.213 vs 0.193

If you are building a fully-probabilistic system where the probability feeds an expected-value calculation against the market’s implied price — which is what Polybot does — calibration is everything, and Kronos’s calibration is bad enough to disqualify it. It thinks it knows more than it does at both ends.

Both interpretations are honest. Neither earns the model a place in Polybot. One of them might earn it a place, later, in TradingAgents — as a 5th analyst voice that votes on direction without being trusted for calibrated odds. That experiment is not what this week tested; it is a separate hypothesis for a separate week.

FIG. 05 — WEEK FOUR · THREE POSSIBLE THREADS

Each is a separate article · the pattern across them is the same

Honest measurement · out-of-sample discipline · no rescue narratives when something doesn’t work

A second-tier candidate model · Amazon’s Chronos

Same general shape as Kronos · different training corpus · also open-source. Running it through the exact same gauntlet would say whether the negative result is specific to Kronos or generalises to learned models in this regime.

Generalisation test

Kronos with a finetune on 5-min crypto data

The Kronos repo ships a finetuning pipeline. Taking the open Kronos-base checkpoint, finetuning on the bot’s own recorded BTC tick history, re-testing. Isolates “is the pretrained distribution wrong for crypto?” from “is the architecture wrong for this horizon?”

Architecture vs distribution

A live-trading update on Polybot

The fleet has been running paper trades continuously across these three weeks. A fresh aggregate-P&L view, with the same calibration-style analysis applied to live performance rather than historical replay, is overdue.

Status reset

The contract is “same gauntlet, different model, same discipline.” Specific numbers stay local. Methodology is public on the repo’s docs/RESEARCH_PIPELINE.md. Publishing reproducible parameter recipes for strategies that might be marginally profitable encourages people to copy them with real money, and the prior on real-money outcomes when copying retail strategies is “they lose.” Publishing the methodology lets the next person test their own model honestly without inheriting any of mine.

By probabilistic standards · Kronos is a worse forecaster. By operational standards · Kronos is the better trader. Both interpretations are honest. Neither earns the model a place in Polybot. One of them might earn it a place, later, in TradingAgents.

Thorsten Meyer AI · Week 3 · Foundation Model vs Brownian Motion

Source dossier & methodology notes

Kronos — Open-source MIT-licensed foundation model for financial time series · 25,000+ stars on GitHub · AAAI 2026 paper · four model sizes (4M · 24.7M open small · 102M open · 499M closed) · trained on candles from 45 global exchanges · authors are explicit it is a research model, not a trading system · github.com/shiyu-coder/Kronos
Polybot — Open-source paper-trading bot · MIT-licensed · runs against Polymarket 5-minute Up/Down crypto markets · fair-value strategy uses geometric Brownian motion · two prior weeks of published research established that most parametric edges are mechanical artefacts
Polymarket 5-min Up/Down — Prediction-market windows on BTC, ETH, and other crypto · the test session: 497 paired (FILL → SETTLE) trades, all BTC · order-book at FILL serves as market-implied probability reference
Test design — Run for every paired trade · reconstruct 60-minute OHLCV context · recompute Brownian baseline (line-for-line port of fairValuePUp(spot, openPrice, secondsLeftFrac, windowVol)) · read market-implied probability · sample 16 Kronos forecast paths · record (p_brownian, p_market, p_kronos, actual_outcome, P&L)
Scoring rules — Brier score (mean squared error of probability vs actual outcome) · log-loss (penalises overconfidence) · hypothetical P&L (counterfactual if Polybot had fired on each model’s probability with the same edge-margin and risk gates) · all reported on first/second half separately
Full-sample (497 trades) — Brier: Brownian 0.193 · Market-implied 0.211 · Kronos 0.213 · Log-loss: Brownian 0.567 · Market-implied 0.604 · Kronos 1.080 · Kronos log-loss ~2× Brownian — confident-wrong-in-tails signature
Out-of-sample (249 trades, test half) — Brownian 0.188 · Kronos 0.189 · gap 0.0011 · well inside the noise band of repeated runs with different Kronos sampling seeds · statistically indistinguishable
Counterfactual P&L — Brownian: 279 fires / 49.1% win rate / +$465 net · Kronos: 201 fires / 60.7% win rate / +$538 net · Kronos fires ~28% less often, wins more reliably, nets slightly more by operational standards
Calibration failures — Kronos predicts 2.4% chance → trades win 20.4% · Kronos predicts 84% chance → trades win 69.6% · systematic overconfidence at both tails
Compute — Mac M-series with PyTorch MPS backend · ~1,300 lines of Python · 11 minutes clock-time · cached to parquet so re-runs cost nothing
Public methodology — docs/RESEARCH_PIPELINE.md on the project repo · same gauntlet runs any future candidate forecast model (Chronos · TimesFM · Lag-Llama · Kronos finetune · other) · sibling directories research//
What this does NOT prove — Not that Kronos is bad (one checkpoint · one horizon · one market) · not that Brownian is good (just not worse at this task; week-2 collapsed at higher sample) · not anything about Stages 2 or 3 of the broader pipeline · negative-Stage-1 kills this candidate at this horizon · the gauntlet does its job
Week 4 candidate threads — (a) Amazon’s Chronos generalisation test · (b) Kronos finetune isolating architecture vs distribution · (c) Polybot live-trading aggregate-P&L update with calibration-style analysis

Colophon

Set in Source Serif 4 (display, italic accent), EB Garamond (body), IBM Plex Sans (UI labels), IBM Plex Mono (mastheads, ticker, tags). Paper-cool gray-cream #e6e7e4.

Chromatic register: structural-slate dominant (methodology + out-of-sample-discipline analysis), empirical-clay for the data forensics, labor-rose for the probabilistic-failure framing and disclaimers, transition-bronze for the operational paradox, alternative-sage for the open-methodology positive signal and the better-trader half of the paradox.

Key frame:

POLYBOT WEEK 3 KRONOS-SMALL · 24.7M BROWNIAN BASELINE OUT-OF-SAMPLE 0.0011 THE PARADOX BETTER TRADER WORSE FORECASTER STAGE 2 NOT HAPPENING SAME GAUNTLET DISCIPLINE HONEST MEASUREMENTS

Implications for Modern AI in Financial Forecasting

This outcome suggests that, at least for short-term, high-frequency Bitcoin trading, advanced foundation models like Kronos do not yet outperform traditional stochastic models such as Brownian motion. It raises questions about the practical benefits of deploying large, complex models for real-time trading decisions and highlights the ongoing challenge of translating AI research into actionable trading advantages.

Amazon

Bitcoin trading algorithm tools

As an affiliate, we earn on qualifying purchases.

Background of Model Testing in Crypto Markets

Previous weeks’ experiments with a simple geometric Brownian motion model revealed that most trading edges identified by a bot were mechanical artifacts that did not persist out-of-sample. This prompted the exploration of whether a modern, learned model trained on extensive market data could do better. Week Three — Foundation model vs Brownian motion. Kronos on five-minute BTC. Kronos, trained on millions of candles from global exchanges and presented as a research tool, was selected for this test. The experiment aimed to compare its out-of-sample predictive performance against the traditional Brownian baseline, specifically in the context of short-term BTC price movements.

“Our tests show that Kronos does not significantly outperform the Brownian baseline in live-simulated trading for 5-minute BTC moves. This highlights the difficulty of translating large models into actionable short-term trading signals.”
— Thorsten Meyer, researcher

Amazon

financial modeling software for cryptocurrencies

As an affiliate, we earn on qualifying purchases.

Limitations and Unanswered Questions in Model Performance

While the test indicates no significant outperformance of Kronos over Brownian motion in this specific scenario, it remains unclear whether different market conditions, longer horizons, or other model configurations might yield different results. Additionally, the potential for model improvements or alternative training approaches to enhance predictive power is still an open question.

Amazon

trading strategy backtesting software

As an affiliate, we earn on qualifying purchases.

Future Directions for AI-Based Short-Term Crypto Trading

Further research could explore alternative models, longer testing periods, or different market conditions to assess whether learned models can eventually surpass traditional stochastic assumptions. Additionally, integrating such models into live trading systems remains a challenge, requiring rigorous validation and risk management strategies.

Amazon

cryptocurrency market analysis tools

As an affiliate, we earn on qualifying purchases.

Key Questions

Does this mean foundation models are useless for crypto trading?

Not necessarily. This study shows that, in this specific context, Kronos did not outperform a simple Brownian model. Future models or different market conditions could produce different results, but current evidence suggests caution in expecting immediate trading advantages from large foundation models.

Could different time horizons yield better results?

Yes, it’s possible that longer or shorter horizons, or different trading strategies, might reveal advantages not seen in this five-minute window. Further testing is needed to explore these possibilities.

Is the experiment conclusive?

The results are statistically robust within the scope of this test, but they do not rule out the potential for future improvements or different market conditions to favor learned models.

What are the implications for traders using AI models?

Traders should remain cautious about relying solely on large AI models for short-term trading signals, especially when current evidence shows no clear edge over traditional assumptions in this setting.

Source: ThorstenMeyerAI.com

Week Three — Foundation model vs Brownian motion. Kronos on five-minute BTC.

Up next

The calendar technicality. Why Elon Musk’s lawsuit against Sam Altman and OpenAI lost on timing, not on substance.

Author

BARRIER MAGZ

Share article

Foundation model
vs Brownian motion.
Kronos on five-minute BTC.