We ran simulated live trades using the AlgoZilla Omniscius v4.2 Theros model for SHIB - Shiba Inu. The results below give you an overview of the most important Key Performance Indicators, Equity Curve and the Trade Log as simulated by our Pythia model. The returns have been accumulated over the February 2025 period. The simulated paper trades of the model show that an initial investment at the start of the period with 18 trades would have compounded to a final value of $13,427 (from a $10,000 base). All results are net of trading fees based on Bitvavo rates (0.15% entry + 0.25% exit). The model uses a 15‑minute delay on the signal on both entries and exits to simulate possible slippage when executing orders.
Shiba Inu (SHIB) emerged as a meme coin in 2020 and has evolved into a broader ecosystem including ShibaSwap DEX and Shibarium Layer 2. With an enormous circulating supply, SHIB trades at fraction-of-a-cent prices but achieves significant market cap through volume. Its extreme volatility and community-driven price action require precise entry and exit timing that algorithmic models excel at.
Shiba Inu (SHIB) — clean monthly entry, no carry-over from previous months. Net of trading fees (Bitvavo 0.15% + 0.25%).
Same coin, same period, same data window — different model. All walk-forward validated. v5.0 (Kairos) is the current production model (live since 11 May 2026); v4.2 (Theros) was the predecessor; v4.0.1 (Pythia) and v4.0 (Itzamná) confirmed the statistical edge during 2025; v2.5 is the legacy baseline.
Δ-arrows on the counterpart cards show this page minus that version. Higher return / WR = better; smaller (less negative) Max DD = better.
1H candles for SHIB over the test window with every entry (▲ green up-arrow) and exit (▼ green = profitable, ▼ red = loss). Hover a marker for trade details.
Aggregates derived from the full 18-trade log of this period.
How the model performs across the 4 market regimes detected by Omniscius.
| Regime | Trades | Win Rate | Avg PnL | Compounded Return | Avg Hold |
|---|---|---|---|---|---|
| SIDEWAYS | 15 | 86.7% | +2.78% | +50.02% | 21h |
| BULL | 1 | 100.0% | +1.29% | +1.29% | 10h |
| BUBBLE | 2 | 50.0% | -0.35% | -0.71% | 3h |
All 18 trades executed during this paper trade period.
| Entry | Exit | Entry Price | Exit Price | PnL | Regime | Duration |
|---|---|---|---|---|---|---|
| 03 Feb 2025 01:00 | 03 Feb 2025 10:00 | $0.00 | $0.00 | +1.29% | BULL | 10h |
| 03 Feb 2025 23:00 | 04 Feb 2025 01:00 | $0.00 | $0.00 | -1.84% | BULL | 3h |
| 04 Feb 2025 09:00 | 04 Feb 2025 11:00 | $0.00 | $0.00 | +1.15% | BUBBLE | 3h |
| 06 Feb 2025 19:00 | 07 Feb 2025 13:00 | $0.00 | $0.00 | +2.84% | SIDEWAYS | 19h |
| 07 Feb 2025 17:00 | 07 Feb 2025 19:00 | $0.00 | $0.00 | +0.77% | SIDEWAYS | 3h |
| 07 Feb 2025 21:00 | 09 Feb 2025 03:00 | $0.00 | $0.00 | +8.97% | SIDEWAYS | 1.3d |
| 09 Feb 2025 21:00 | 11 Feb 2025 05:00 | $0.00 | $0.00 | +3.73% | SIDEWAYS | 1.4d |
| 11 Feb 2025 14:00 | 11 Feb 2025 16:00 | $0.00 | $0.00 | +0.16% | SIDEWAYS | 3h |
| 11 Feb 2025 19:00 | 12 Feb 2025 22:00 | $0.00 | $0.00 | +8.20% | SIDEWAYS | 1.2d |
| 13 Feb 2025 13:00 | 14 Feb 2025 16:00 | $0.00 | $0.00 | +3.34% | SIDEWAYS | 1.2d |
| 14 Feb 2025 23:00 | 15 Feb 2025 01:00 | $0.00 | $0.00 | +0.67% | SIDEWAYS | 3h |
| 15 Feb 2025 17:00 | 15 Feb 2025 21:00 | $0.00 | $0.00 | -0.41% | SIDEWAYS | 5h |
| 16 Feb 2025 03:00 | 16 Feb 2025 05:00 | $0.00 | $0.00 | -0.04% | SIDEWAYS | 3h |
| 17 Feb 2025 18:00 | 17 Feb 2025 22:00 | $0.00 | $0.00 | +0.94% | SIDEWAYS | 5h |
| 18 Feb 2025 07:00 | 18 Feb 2025 10:00 | $0.00 | $0.00 | +0.64% | SIDEWAYS | 4h |
| 18 Feb 2025 15:00 | 21 Feb 2025 01:00 | $0.00 | $0.00 | +1.16% | SIDEWAYS | 2.5d |
| 21 Feb 2025 20:00 | 23 Feb 2025 01:00 | $0.00 | $0.00 | +3.30% | SIDEWAYS | 1.3d |
| 25 Feb 2025 01:00 | 27 Feb 2025 06:00 | $0.00 | $0.00 | +7.49% | SIDEWAYS | 2.3d |
A paper trade simulates real signal execution without real money. Each period starts fresh with a clean $10,000 allocation — no carry-over from previous windows. This shows exactly what would have happened if you started following signals on day one of that window. View live SHIB signals →
Yes. All results are net of trading fees based on Bitvavo rates (0.15% entry + 0.25% exit). No slippage is applied. Trading via Bitget (0.1%/0.1%) would improve returns.
Paper trades use the same model and signals as the full backtest. The difference: backtests cover years of data across multiple market cycles, while paper trades show month-by-month performance in recent market conditions. Together they provide a complete picture.
Yes. The Omniscius model is retrained bi-weekly, which means paper trade results reflect the exact same model updates that live subscribers receive. This is not a static backtest — it is a living simulation. Learn about Omniscius →
These paper trade results show what our model delivers. Get real-time SHIB signals with entry, stop-loss, and take-profit on every trade.
Institutional-grade AI trading signals for crypto traders. Our ensemble models use strict walk-forward validation across multiple Bitcoin halving cycles. No curve-fitting, no hype — just data-driven signals delivered to your Telegram. Methodology and changelog are public on our About page.
Prices delayed up to 5 minutes. Trading and investing involve significant risk of loss. All content on this site is for informational purposes only and does not constitute financial advice. Decisions to buy, sell, or hold are best made with the advice of qualified financial professionals. Past performance does not guarantee future results.
Hypothetical or simulated performance results have inherent limitations. Unlike an actual performance record, simulated results do not represent actual trading. Since the trades have not been executed, the results may have under- or over-compensated for the impact of certain market factors, including lack of liquidity. No representation is being made that any account will or is likely to achieve profit or losses similar to those shown.
Some links on this site are affiliate links. AlgoZilla may earn a commission at no extra cost to you. This does not affect signal quality. Please read our full disclaimer · Terms · Privacy
© 2026 AlgoZilla.io — All rights reserved