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

📊 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 Kronos, a foundation model, against a Brownian motion baseline for 5-minute Bitcoin predictions found no significant advantage. The study used historical trade data and out-of-sample testing to evaluate performance.

Recent testing shows that Kronos, an open-source foundation model, trained on global cryptocurrency data, does not outperform a traditional Brownian motion model in predicting 5-minute Bitcoin (BTC) price movements.

The study involved a detailed, out-of-sample comparison between Kronos-small and a geometric Brownian motion baseline across 497 historical BTC trades recorded by the Polybot trading simulator. The models’ predictions were evaluated using Brier scores, log-loss, and hypothetical profit-and-loss metrics.

Results indicate that Kronos’s predictive performance is statistically indistinguishable from Brownian motion, with both models showing similar accuracy and risk profiles on the last half of the test data, which was never seen during training. Specifically, the Brier scores for Kronos and Brownian were 0.213 and 0.193 respectively, with differences falling within the margin of statistical noise.

Despite the advanced training and larger parameter sizes, Kronos did not demonstrate a clear edge over the traditional model at the 5-minute horizon used by the trading bot. Consequently, the authors conclude that integrating Kronos into the current trading pipeline as a live predictive strategy is not justified based on these results.

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.
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
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

Implications for AI-based Crypto Trading Strategies

This finding challenges assumptions that modern, learned models will automatically outperform classical stochastic models like Brownian motion in short-term crypto prediction. It suggests that, at least for the tested horizon and data, the complexity of a foundation model does not necessarily translate into improved trading signals.

For traders and developers, this highlights the importance of rigorous out-of-sample testing before deploying AI models in live environments. The results also underscore the resilience of simple probabilistic models in certain high-frequency trading contexts, especially when market dynamics deviate from assumptions like independence and normality.

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…

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Background and Prior Testing of Market Models

Over the past two weeks, the author conducted open-source paper trading experiments using Polybot against Polymarket’s 5-minute Up/Down markets, revealing that most strategies lacked genuine edge, with only one exhibiting a marginal advantage that collapsed under more extensive testing.

The initial approach relied on a geometric Brownian motion model, a 100-year-old mathematical assumption that estimates the probability of BTC closing above a certain price based on independent, normally-distributed log-returns. Given the market’s complexity, the question arose whether a modern, learned model trained on millions of candlestick data could outperform this baseline.

Kronos, a recent foundation model trained on 45 global exchanges, was identified as a promising candidate for this purpose. It is designed for research rather than trading, with multiple sizes and an explicit disclaimer against direct trading use. The current testing aimed to evaluate its predictive power in a real-world, out-of-sample setting.

“Despite its sophistication, Kronos does not outperform the traditional Brownian baseline in short-term BTC predictions under the tested conditions.”

— Thorsten Meyer, researcher

WiFi Bitcoin Crypto Tracker Bitcoin Crypto Price Displayer Currency,Stocks,Futures,Currency Exchange Rate,Price Tracker Ticker,Time Clock Weather Display

WiFi Bitcoin Crypto Tracker Bitcoin Crypto Price Displayer Currency,Stocks,Futures,Currency Exchange Rate,Price Tracker Ticker,Time Clock Weather Display

【Real-Time 300+ Crypto Price Tracking】 Instantly monitors 300+ mainstream cryptocurrencies (BTC, ETH, SOL, etc.) with Binance API-powered data….

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Unclear Impact of Model Complexity on Short-Term Prediction

It remains uncertain whether different configurations of Kronos, larger parameter sizes, or alternative training data might yield better performance. Additionally, the test focused solely on 5-minute horizons; results could differ at other time scales or market conditions.

Furthermore, the potential for model improvements or hybrid strategies combining traditional and learned models has not been explored in this study.

Excel Data Analysis For Dummies (For Dummies (Computer/Tech))

Excel Data Analysis For Dummies (For Dummies (Computer/Tech))

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Next Steps for AI Crypto Prediction Research

Further research is expected to explore whether model tuning, larger datasets, or different architectures can improve predictive accuracy. Developers may also investigate hybrid approaches that combine stochastic models with machine learning.

In addition, ongoing testing in live trading environments will be necessary to confirm whether these findings hold under real market conditions and across different assets or time horizons.

How to Day Trade for Beginners: Master Trading Tools, Risk Management, Psychology, and Technical Analysis to Build a Profitable Career in Stock Market, Crypto, Futures, and Options Trading Basics

How to Day Trade for Beginners: Master Trading Tools, Risk Management, Psychology, and Technical Analysis to Build a Profitable Career in Stock Market, Crypto, Futures, and Options Trading Basics

As an affiliate, we earn on qualifying purchases.

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, at least for 5-minute BTC predictions, Kronos did not outperform a simple Brownian motion baseline. Further research could reveal benefits at other horizons or with different models.

Could larger or differently trained models perform better?

It is possible. The current results are specific to the tested configuration. Future experiments with larger models or alternative training data may produce different outcomes.

What does this mean for traders using AI models?

It underscores the importance of rigorous out-of-sample testing and skepticism of assumptions that more complex models automatically outperform simpler ones in short-term trading contexts.

Will Kronos be integrated into trading strategies in the future?

Based on current results, not immediately. The study concludes that Kronos does not provide a clear advantage over traditional models at this horizon, but further testing could change that assessment.

Source: ThorstenMeyerAI.com

You May Also Like

Why Lifestyle Businesses and Scalable Businesses Create Different Wealth

A comparison of lifestyle and scalable businesses reveals how their unique approaches to growth and wealth can impact your financial future—discover which path suits you best.

Mesh WiFi vs WiFi Extenders: The Truth Nobody Tells You

Better WiFi coverage depends on understanding the hidden truths between mesh systems and extenders; discover which option truly delivers seamless connectivity.

ESG Investing: Does It Really Sacrifice Returns?

Optimizing your investments with ESG factors may surprise you—discover whether prioritizing sustainability and governance genuinely impacts returns.