Week Three — Foundation model vs Brownian motion. Kronos on five-minute BTC.
Up next
Author
Share article
The post has been shared by 0 people.
Facebook 0
X (Twitter) 0
Pinterest 0
Mail 0

📊 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 compared Kronos, a foundation model, to the traditional Brownian motion model for predicting 5-minute Bitcoin price movements. The results show Kronos performs similarly to Brownian, with no statistically significant edge, challenging assumptions about AI outperforming classical models in this context.

Recent testing shows that Kronos, a foundation model trained on millions of candlestick data, does not outperform the traditional Brownian motion model in predicting 5-minute Bitcoin price movements, with both models demonstrating similar predictive accuracy.

The test involved applying Kronos-small, an open-source foundation model, to a dataset of 497 past BTC trades recorded by Polybot, a simulated trading bot. The models’ predictions were evaluated using metrics such as Brier score, log-loss, and hypothetical profit and loss. Results showed that Kronos’s prediction accuracy was statistically indistinguishable from Brownian motion, the classical model based on geometric Brownian assumptions, both on the full sample and on a separate out-of-sample subset of 249 trades. Specifically, the Brier scores for Brownian and Kronos were 0.193 and 0.213 respectively on the full sample, with only a marginal difference of 0.0011 on the out-of-sample trades, which is within the margin of statistical noise. Consequently, the test concluded that Kronos does not provide a meaningful edge over the traditional model for the specific trading horizon and market conditions tested. The implications are significant: despite the sophistication and scale of Kronos, it did not outperform a simple, well-understood classical model in this scenario, challenging assumptions about the superiority of modern AI models in short-term crypto prediction.

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
1
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.
2
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.
3
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.
4
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).
5
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
1
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
2
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
3
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 AI-based Trading Strategies

This finding questions the assumption that advanced foundation models automatically yield better predictive performance in financial markets, especially in short-term trading. For traders and developers, it highlights the importance of rigorous testing and skepticism about AI claims of superior performance. The result also suggests that classical models like Brownian motion remain relevant benchmarks, and that the complexity of modern models does not guarantee practical advantage in all market conditions.

Scalp Smart Hacks to Win Big in Forex Day Trading: Welcome to Scalp Smart, the comprehensive guide designed to transform your forex scalping journey from guesswork to consistent profits.

Scalp Smart Hacks to Win Big in Forex Day Trading: Welcome to Scalp Smart, the comprehensive guide designed to transform your forex scalping journey from guesswork to consistent profits.

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Background of Model Testing and Market Expectations

Over recent years, foundation models like Kronos have gained attention for their potential to improve financial predictions by leveraging large-scale data and machine learning techniques. Prior to this test, many believed that such models could outperform traditional stochastic models, especially in volatile markets like cryptocurrencies. The testing follows an initial two-week experiment with a trading bot that used a Brownian motion-based model, which showed limited success in identifying persistent edges. The development of Kronos, trained on extensive global exchange data, was seen as a promising alternative. However, the current results indicate that, at least for the specific 5-minute horizon in BTC trading, the modern foundation model does not outperform the classical approach.

“Despite the scale and sophistication of Kronos, it does not outperform the traditional Brownian model in short-term BTC prediction under the tested conditions.”

— Thorsten Meyer, AI researcher and author

Crypto Seed Cold Storage Wallet with Engraver Pen Kit - Metal Plate and Etching Tool for Cryptocurrency Password Phrase Backup and Recovery

Crypto Seed Cold Storage Wallet with Engraver Pen Kit – Metal Plate and Etching Tool for Cryptocurrency Password Phrase Backup and Recovery

All Inclusive Kit for Crypto Seed Key Storage – Comes a Stainless Steel Plate & Tungsten Steel Engraving…

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Limitations and Conditions of the Testing Approach

While the test was comprehensive within its scope, it remains uncertain whether Kronos might outperform in different market conditions, timeframes, or with alternative trading strategies. The model was evaluated on a specific 5-minute horizon and a particular dataset, which may not capture all market complexities. Additionally, the models’ performance could vary with live trading conditions, including slippage, transaction costs, and market impact, which were not incorporated into this simulation.

Ultimate Beginner's Guide to Crypto Trading Bots

Ultimate Beginner's Guide to Crypto Trading Bots

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Future Research and Potential Model Improvements

Further testing across different timeframes, assets, and market regimes is needed to fully assess Kronos’s capabilities. Researchers may also explore hybrid approaches combining classical models with AI, or refine training data and model architectures. For traders, the key takeaway is to maintain rigorous validation and avoid overreliance on AI predictions without empirical backing. The ongoing development of foundation models will likely continue, but their practical advantages in short-term crypto trading remain to be conclusively demonstrated.

Vastarry Crypto Price Ticker Display - WiFi Bitcoin Ethereum Real-Time Dashboard, Desktop LED Monitor for Cryptocurrency Gold Silver Prices, Smart Investment Gift for Traders

Vastarry Crypto Price Ticker Display – WiFi Bitcoin Ethereum Real-Time Dashboard, Desktop LED Monitor for Cryptocurrency Gold Silver Prices, Smart Investment Gift for Traders

Multi-Market Coverage Supports cryptocurrencies, spot gold, spot silver, forex, US stocks, Hong Kong stocks, and A-shares. Cryptocurrency data…

AmazonView Latest Price

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Key Questions

Does this mean AI models are useless for crypto trading?

Not necessarily. This specific test shows that Kronos did not outperform a classical model in this scenario. AI models may have advantages in other contexts, but rigorous testing is essential before relying on them for trading decisions.

Could Kronos perform better with different data or settings?

Potentially. The current results are limited to a specific dataset, timeframe, and market conditions. Further research could explore different configurations, assets, or longer horizons.

What does this mean for traders using AI tools?

It underscores the importance of empirical validation. Traders should be cautious about claims of AI superiority and rely on proven, tested strategies rather than assumptions.

Will Kronos be improved to outperform classical models?

Future developments may enhance Kronos, but current results suggest that improvements are necessary before it can reliably outperform traditional methods in short-term crypto trading.

Source: ThorstenMeyerAI.com

This content is for general information only and is not financial, tax or legal advice. Consult a qualified professional for decisions about your money.
You May Also Like
The Skills Marketplace Nobody Is Building Yet

The Skills Marketplace Nobody Is Building Yet

A new standard for AI skills exists, but a marketplace layer for discovery, monetization, and security is still absent, leaving a critical gap in AI infrastructure.
Technology operations signal monitor: Show HN: Kage – Shadow any website to a single binary for offline viewing

Technology operations signal monitor: Show HN: Kage – Shadow any website to a single binary for offline viewing

Kage is a new tool that allows users to shadow any website into a single binary for offline access, aimed at product and engineering leads to monitor platform changes.
Forezai · Polybot: When the AI Disagrees With the Odds

Forezai · Polybot: When the AI Disagrees With the Odds

Polybot, an open-source AI trading experiment, tests when and how an AI can reliably disagree with prediction market odds, highlighting risks and calibration issues.
Forward-Deployed Engineer Economics 2.0: The Unit Economics Math, Six Months Later

Forward-Deployed Engineer Economics 2.0: The Unit Economics Math, Six Months Later

An update on FDE economics reveals profitability at scale, driven by actual contract sizes and costs, with implications for enterprise AI deployment and lab scaling.