AI Agent Backtest of a Leveraged ETF Strategy Versus SPY
Document Lumibot
Summary
The document presents a QuantStats tear sheet for a strategy labeled tqqq-plain, compared with SPY. It reports a short backtest covering January 4–15, 2026, using Yahoo data, alongside return, drawdown, volatility, risk-adjusted performance, and benchmark comparison statistics. The parameter section lists a universe of leveraged long and inverse ETFs and describes researcher, bull, bear, and trader agents used by the system.
The report gives a snapshot of simulated performance, but it does not explain the trading rules, signal construction, position sizing, or transaction cost assumptions. Its brief sample makes the annualized figures and risk metrics especially weak evidence for durable performance. The tear sheet also includes an unusually high strategy return alongside substantial volatility and drawdown, underscoring that the headline statistics need careful scrutiny and longer, reproducible testing before interpretation.
Key ideas
- The report compares a strategy labeled tqqq-plain with SPY over a short January 2026 period.
- It presents return, drawdown, volatility, and risk-adjusted statistics from a QuantStats tear sheet.
- The listed system uses multiple AI agents and a universe of leveraged long and inverse ETFs.
- The document omits the strategy rules and transaction cost assumptions needed to reproduce the results.
- Annualized metrics derived from the short sample do not establish long-term performance.
Tags
Full text
# tqqq strategy ai trading bot
Tearsheet (generated by QuantStats)
tqqq-plain Compared to SPY 4 Jan, 2026 - 15 Jan, 2026
Benchmark is SPY | LumiBot 4.6.3 | DataSource yahoo | Backtest time 21:27 | Generated by QuantStats (Lumiwealth Version) (v.1.1.5)
Annual Return ⓘ
210.93%
Total Return ⓘ
3%
Max Drawdown ⓘ
-4.05%
RoMaD ⓘ
52.14
Longest DD Days ⓘ
4
Sharpe ⓘ
2.62
Sortino ⓘ
4.23
Key Performance Metrics
MetricSPYStrategy
Risk-Free Rate3.56%3.56%
Time in Market67.0%75.0%
Total Return1%3%
CAGR% (Annual Return)24.3%210.93%
Sharpe2.592.62
RoMaD35.1952.14
Corr to Benchmark1.0-0.06
Prob. Sharpe Ratio67.18%63.6%
Smart Sharpe1.661.68
Sortino4.734.23
Smart Sortino3.022.7
Sortino/√23.352.99
Smart Sortino/√22.141.91
Omega1.51.49
Max Drawdown-0.69%-4.05%
Longest DD Days34
Volatility (ann.)6.41%41.3%
R^20.00.0
Information Ratio0.110.11
Calmar35.1952.14
Skew0.45-0.19
Kurtosis0.140.73
Expected Daily%0.05%0.29%
Expected Monthly%0.66%3.48%
Expected Yearly%0.66%3.48%
Daily Value-at-Risk-0.5%-3.25%
Expected Shortfall (cVaR)-0.5%-4.05%
MTD0.66%3.48%
3M0.66%3.48%
6M0.66%3.48%
YTD0.66%3.48%
1Y0.66%3.48%
3Y (ann.)24.3%210.93%
5Y (ann.)24.3%210.93%
10Y (ann.)24.3%210.93%
All-time (ann.)24.3%210.93%
Best Day0.66%4.22%
Worst Day-0.49%-4.05%
Best Month0.66%3.48%
Worst 1-Month Return0.66%3.48%
Best Year0.66%3.48%
Worst Year0.66%3.48%
Avg. Drawdown-0.51%-2.42%
Avg. Drawdown Days22
Recovery Factor0.960.91
Ulcer Index0.00.02
Serenity Index-4.90.04
Annualized Return on Risk Capital2,895.24%2,613.07%
Worst 3-Month Return--
Time to Recovery (Days)11
5th Percentile Tail Loss-0.4%-2.72%
Time Underwater (Days)57
Percent Positive Months100.0100.0
Avg. Up Month0.66%3.48%
Avg. Down Month--
Win Days6.08.0
Loss Days6.04.0
Win Days%50.0%66.67%
Win Month%100.0%100.0%
Win Quarter%100.0%100.0%
Win Year%100.0%100.0%
Beta--0.4
Alpha-1.2
Correlation--6.26%
Treynor Ratio-0.2%
EOY Returns vs Benchmark
YearSPYStrategyMultiplierWon
20260.663.485.29+
Worst 10 Drawdowns
StartedRecoveredDrawdownDays
2026-01-052026-01-06-4.052
2026-01-092026-01-12-1.644
2026-01-152026-01-15-1.561
2026-09-29T23:17:24.653021
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:24.706149
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:24.757012
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:24.827784
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:24.879616
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:24.935037
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:25.002639
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:25.066043
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:25.128578
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:25.183847
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:25.230311
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:25.289092
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:17:25.346843
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
Disclaimer: This report is for informational purposes only and
should not be considered as investment advice. Past performance
is not indicative of future results.
Parameters Used
ParameterValue
universe['TQQQ', 'SQQQ', 'UPRO', 'SPXU', 'UDOW', 'SDOW', 'TNA', 'TZA', 'SOXL', 'SOXS', 'TMF', 'TMV']
agent_max_model_calls200
agent_researcher_modelopenai/gpt-6-luna
agent_bull_modelopenai/gpt-6-luna
agent_bear_modelopenai/gpt-6-luna
agent_trader_modelopenai/gpt-6-luna
agent_model_calls36
agent_researcher_calls9
agent_researcher_cache_hits0
agent_researcher_tool_calls39
agent_researcher_input_tokens713685
agent_researcher_output_tokens15996
agent_researcher_total_tokens729681
agent_researcher_thinking_tokens5808
agent_researcher_cached_input_tokens621422
agent_researcher_cache_write_input_tokens0
agent_researcher_uncached_input_tokens92263
agent_researcher_tool_use_input_tokens0
agent_researcher_latency_ms_total194264
agent_researcher_latency_ms_avg21584.89
agent_researcher_first_event_latency_ms_avg3423.22
agent_researcher_detail_parquetlogs/tqqq-plain_2026-09-29_22-55_zpFipV_agent_detail.parquet
agent_bear_calls9
agent_bear_cache_hits0
agent_bear_tool_calls55
agent_bear_input_tokens721973
agent_bear_output_tokens19039
agent_bear_total_tokens741012
agent_bear_thinking_tokens8040
agent_bear_cached_input_tokens627311
agent_bear_cache_write_input_tokens0
agent_bear_uncached_input_tokens94662
agent_bear_tool_use_input_tokens0
agent_bear_latency_ms_total214393
agent_bear_latency_ms_avg23821.44
agent_bear_first_event_latency_ms_avg4154.33
agent_bear_detail_parquetlogs/tqqq-plain_2026-09-29_22-55_zpFipV_agent_detail.parquet
agent_bull_calls9
agent_bull_cache_hits0
agent_bull_tool_calls63
agent_bull_input_tokens779132
agent_bull_output_tokens16610
agent_bull_total_tokens795742
agent_bull_thinking_tokens7343
agent_bull_cached_input_tokens682463
agent_bull_cache_write_input_tokens0
agent_bull_uncached_input_tokens96669
agent_bull_tool_use_input_tokens0
agent_bull_latency_ms_total208087
agent_bull_latency_ms_avg23120.78
agent_bull_first_event_latency_ms_avg3864.0
agent_bull_detail_parquetlogs/tqqq-plain_2026-09-29_22-55_zpFipV_agent_detail.parquet
agent_trader_calls9
agent_trader_cache_hits0
agent_trader_tool_calls206
agent_trader_input_tokens2723022
agent_trader_output_tokens71485
agent_trader_total_tokens2794507
agent_trader_thinking_tokens56715
agent_trader_cached_input_tokens2578399
agent_trader_cache_write_input_tokens0
agent_trader_uncached_input_tokens144623
agent_trader_tool_use_input_tokens0
agent_trader_latency_ms_total860624
agent_trader_latency_ms_avg95624.89
agent_trader_first_event_latency_ms_avg3344.56
agent_trader_detail_parquetlogs/tqqq-plain_2026-09-29_22-55_zpFipV_agent_detail.parquet
BACKTESTING_DATA_SOURCEyahooShown in full with attribution under the source's licence. Licence: GPL-3.0
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.