APOLLO V9.3 — Deploying $20K on Czech Liga Pro Table Tennis
Czech Liga Pro is a high-frequency table tennis league operating 12+ hours daily with minimal bookmaker attention. Market-makers rely on generic algorithms, creating persistent mispricings in player-specific fatigue dynamics that sophisticated models can exploit.
Physical fatigue is the dominant unpriced factor in continuous table tennis leagues. Players competing in 6+ matches per day exhibit measurable performance degradation that bookmaker odds fail to incorporate. Our residual model captures this systematic error.
Replication requires 113K+ match historical dataset, proprietary feature engineering pipeline, domain-specific Elo tracking, and real-time state management infrastructure. The data collection alone represents 18+ months of continuous ingestion from a specialized API vendor.
| Time | Asset | Signal | Odds | Edge% | Stake | PnL | Result |
|---|
Note: This is a live tracking period with real capital. All metrics update in real-time as bets are placed and resolved. Bets marked CASHOUT reflect early position exits with actual P&L (payout minus wager), not model-driven resolutions.
Gradient-boosted decision trees trained on 69K+ historical matches. Residual architecture predicts bookmaker error, not raw outcome.
5-fold cross-validated probability calibration. Maps model scores to true event frequencies. Brier CV: 0.1496.
Fractional Kelly criterion with Brier-scaled dynamic brake. Auto-deleverages when model calibration drifts beyond tolerance.
| Metric | Value |
|---|---|
| ROI / Bet (OOS) | +2.71% |
| Sharpe Ratio (annualized) | 1.87 |
| Max Drawdown | 3.30% |
| Feature Families | 5 (8 residual signals) |
| Total Bets (OOS) | 4,204 |
| Test-Match Universe | 36,908 |
| 2σ Sharpe Hurdle | 1.92 |
Signals α through ε represent 5 proprietary feature families covering Fatigue & Recovery, Skill & Rating, Form & Momentum, Market Pricing, and Contextual dimensions. Exact family-to-signal mappings are withheld; qualified investors may request the decoded breakdown under NDA.
Every claim is backed by institutional-grade validation. We use techniques from Marcos López de Prado’s Advances in Financial Machine Learning to prevent overfitting and ensure genuine predictive power.
Combinatorially Purged Cross-Validation
Eliminates information leakage between train/test folds by purging overlapping temporal data. Standard k-fold is invalid for time-series betting data — CPCV is the gold standard.
4,204 OOS Bets · 36,908 Test Matches
Sequential out-of-sample testing that mimics real deployment. The V9.3 model is trained on chronologically prior data and evaluated on a strictly future window with point-in-time feature state.
Sharpe CI₉₅: [−0.29, +4.00]
10,000-iteration block bootstrap on the OOS bet log. CI₉₅ is reported honestly: V9.3 has a positive Sharpe point estimate (+1.87) but the lower bound straddles zero, consistent with a thin-edge system requiring continued sample accumulation.
| Metric | Value |
|---|---|
| Total Bets (OOS) | 4,204 |
| ROI per Bet | +2.71% |
| Sharpe Ratio (annualized) | 1.87 |
| Sharpe 95% CI | [−0.29, +4.00] |
| Max Drawdown | 3.30% |
| Live Model Brier | 0.2403 |
| Live Bookmaker Brier | 0.2423 |
Backtest results from V9.3 walk-forward evaluation (36,908 test matches, 4,204 qualifying bets) with no look-ahead bias. Sharpe CI₉₅ reported honestly: V9.3 is a directionally positive, statistically thin-edge system. Live shadow-trader Brier (0.2403 vs bookmaker 0.2423) confirms the model is marginally better calibrated than the market on resolved live bets.
Matches evaluated at T-30min with finalized player state. Eliminates phantom rest artifacts from early API polling.
Bankroll reconstructed deterministically from first principles: $20,000 + SUM(PnL) - SUM(sweeps). Immune to state corruption.
Profits above the high-water mark swept to reserve ledger, resetting operating bankroll. Locks in realized gains.
Matches >30min out logged to market_projections for research. Re-evaluated with fresh state when entering JIT window.
Disclaimer: Past performance does not guarantee future results. All trading and wagering involves risk of loss. This system deploys real capital and results shown reflect actual positions taken. Not investment advice.