Interpreting a Short AI Trading Bot Backtest Against SPY
Summary
This document is a QuantStats tear sheet comparing an AI trading strategy with SPY over a brief January 2026 backtest, using Yahoo data. It reports a 1% total return for each, with the strategy showing a higher annualized return estimate but also a larger maximum drawdown and greater annualized volatility. The tear sheet includes risk-adjusted measures, benchmark correlation, time in the market, daily return statistics, and drawdown episodes. It identifies the software and data source, and lists model-call and tool-use counts among the run parameters.
The report provides descriptive output rather than a strategy explanation: it does not state the bot’s signals, asset selection, trading rules, or execution assumptions. The very short evaluation window makes annualized figures and related statistics poor evidence of durable performance. Its own disclaimer cautions that past performance does not predict future results, and the comparison alone does not establish that the strategy has a repeatable edge.
Key ideas
- The tear sheet compares a bot’s reported returns and risk metrics with SPY over a short January 2026 period.
- Both the strategy and benchmark show the same reported total return, while the strategy has higher reported volatility and drawdown.
- The report gives benchmark correlation, risk-adjusted metrics, exposure time, and drawdown episodes.
- It does not describe the trading rules, and the brief sample limits conclusions from annualized statistics.
Tags
Full text
# make me money ai trading bot
Tearsheet (generated by QuantStats)
make-money-generic Compared to SPY 4 Jan, 2026 - 15 Jan, 2026
Benchmark is SPY | LumiBot 4.6.3 | DataSource yahoo | Backtest time 5:54 | Generated by QuantStats (Lumiwealth Version) (v.1.1.5)
Annual Return ⓘ
29.51%
Total Return ⓘ
1%
Max Drawdown ⓘ
-1.38%
RoMaD ⓘ
21.4
Longest DD Days ⓘ
4
Sharpe ⓘ
1.67
Sortino ⓘ
2.6
Key Performance Metrics
MetricSPYStrategy
Risk-Free Rate3.56%3.56%
Time in Market67.0%75.0%
Total Return1%1%
CAGR% (Annual Return)24.3%29.51%
Sharpe2.591.67
RoMaD35.1921.4
Corr to Benchmark1.00.07
Prob. Sharpe Ratio67.18%58.63%
Smart Sharpe1.711.1
Sortino4.732.6
Smart Sortino3.131.72
Sortino/√23.351.84
Smart Sortino/√22.211.21
Omega1.51.33
Max Drawdown-0.69%-1.38%
Longest DD Days34
Volatility (ann.)6.41%12.53%
R^20.00.0
Information Ratio0.020.02
Calmar35.1921.4
Skew0.45-0.18
Kurtosis0.142.57
Expected Daily%0.05%0.06%
Expected Monthly%0.66%0.78%
Expected Yearly%0.66%0.78%
Daily Value-at-Risk-0.5%-1.01%
Expected Shortfall (cVaR)-0.5%-1.38%
MTD0.66%0.78%
3M0.66%0.78%
6M0.66%0.78%
YTD0.66%0.78%
1Y0.66%0.78%
3Y (ann.)24.3%29.51%
5Y (ann.)24.3%29.51%
10Y (ann.)24.3%29.51%
All-time (ann.)24.3%29.51%
Best Day0.66%1.4%
Worst Day-0.49%-1.38%
Best Month0.66%0.78%
Worst 1-Month Return0.66%0.78%
Best Year0.66%0.78%
Worst Year0.66%0.78%
Avg. Drawdown-0.51%-0.68%
Avg. Drawdown Days22
Recovery Factor0.960.58
Ulcer Index0.00.0
Serenity Index-4.9-2.97
Annualized Return on Risk Capital2,895.24%1,724.48%
Worst 3-Month Return--
Time to Recovery (Days)10
5th Percentile Tail Loss-0.4%-0.82%
Time Underwater (Days)56
Percent Positive Months100.0100.0
Avg. Up Month0.66%0.78%
Avg. Down Month--
Win Days6.06.67
Loss Days6.05.33
Win Days%50.0%55.56%
Win Month%100.0%100.0%
Win Quarter%100.0%100.0%
Win Year%100.0%100.0%
Beta-0.13
Alpha-0.22
Correlation-6.54%
Treynor Ratio--21.72%
EOY Returns vs Benchmark
YearSPYStrategyMultiplierWon
20260.660.781.19+
Worst 10 Drawdowns
StartedRecoveredDrawdownDays
2026-01-052026-01-05-1.381
2026-01-152026-01-15-0.351
2026-01-092026-01-12-0.314
2026-09-29T23:20:59.963776
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.012686
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.057302
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.120567
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.165438
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.215164
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.273429
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.329777
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.389067
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.442153
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.485815
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.545055
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:21:00.601012
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
agent_max_model_calls40
agent_trader_modelopenai/gpt-6-luna
agent_model_calls9
agent_trader_calls9
agent_trader_cache_hits0
agent_trader_tool_calls122
agent_trader_input_tokens1155284
agent_trader_output_tokens23260
agent_trader_total_tokens1178544
agent_trader_thinking_tokens13126
agent_trader_cached_input_tokens1068484
agent_trader_cache_write_input_tokens0
agent_trader_uncached_input_tokens86800
agent_trader_tool_use_input_tokens0
agent_trader_latency_ms_total352906
agent_trader_latency_ms_avg39211.78
agent_trader_first_event_latency_ms_avg3835.33
agent_trader_detail_parquetlogs/make-money-generic_2026-09-29_23-15_MAIaA3_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.