Evaluating a Short-Horizon AI Stock Portfolio Against SPY
Document Lumibot
Summary
This report compares an AI-driven portfolio built from a named set of large-company stocks with SPY over a very short backtest window. It presents standard performance and risk measures, including returns, drawdown, Sharpe and Sortino ratios, benchmark correlation, and daily win and loss statistics. In the displayed period, the strategy lost money while SPY gained, and the strategy's risk-adjusted measures were negative.
The report also lists model-call and data-use diagnostics for researcher, short-seller, and trader agents, alongside the data source and risk-free rate used. These details offer some transparency about the workflow, but the document does not describe the portfolio's decision rules, position sizing, or execution assumptions. Its brief test window and internal inconsistencies among some reported metrics make the figures inadequate evidence of durable performance; the report itself cautions that past results do not predict future outcomes.
Key ideas
- The report benchmarks a model-driven stock portfolio against SPY.
- It provides return, drawdown, risk-adjusted, and benchmark comparison metrics.
- The strategy underperformed SPY during the displayed test window.
- The short evaluation period and missing strategy details limit what can be inferred.
Tags
Full text
# bill ackman portfolio ai trading bot
Tearsheet (generated by QuantStats)
ackman-plain Compared to SPY 4 Jan, 2026 - 15 Jan, 2026
Benchmark is SPY | LumiBot 4.6.3 | DataSource yahoo | Backtest time 19:04 | Generated by QuantStats (Lumiwealth Version) (v.1.1.5)
Annual Return ⓘ
-26.34%
Total Return ⓘ
-1%
Max Drawdown ⓘ
-0.92%
RoMaD ⓘ
-28.74
Longest DD Days ⓘ
1
Sharpe ⓘ
-6.21
Sortino ⓘ
-6.14
Key Performance Metrics
MetricSPYStrategy
Risk-Free Rate3.56%3.56%
Time in Market67.0%9.0%
Total Return1%-1%
CAGR% (Annual Return)24.3%-26.34%
Sharpe2.59-6.21
RoMaD35.19-28.74
Corr to Benchmark1.0-0.2
Prob. Sharpe Ratio67.18%1.23%
Smart Sharpe--
Sortino4.73-6.14
Smart Sortino--
Sortino/√23.35-4.34
Smart Sortino/√2--
Omega1.50.0
Max Drawdown-0.69%-0.92%
Longest DD Days31
Volatility (ann.)6.41%5.05%
R^20.040.04
Information Ratio-0.28-0.28
Calmar35.19-28.74
Skew0.45-3.46
Kurtosis0.1412.0
Expected Daily%0.05%-0.08%
Expected Monthly%0.66%-0.92%
Expected Yearly%0.66%-0.92%
Daily Value-at-Risk-0.5%-0.51%
Expected Shortfall (cVaR)-0.5%-0.92%
MTD0.66%-0.92%
3M0.66%-0.92%
6M0.66%-0.92%
YTD0.66%-0.92%
1Y0.66%-0.92%
3Y (ann.)24.3%-26.34%
5Y (ann.)24.3%-26.34%
10Y (ann.)24.3%-26.34%
All-time (ann.)24.3%-26.34%
Best Day0.66%0.0%
Worst Day-0.49%-0.92%
Best Month0.66%-0.92%
Worst 1-Month Return0.66%-0.92%
Best Year0.66%-0.92%
Worst Year0.66%-0.92%
Avg. Drawdown-0.51%-0.92%
Avg. Drawdown Days21
Recovery Factor0.961.0
Ulcer Index0.00.0
Serenity Index-4.9-4.67
Annualized Return on Risk Capital2,895.24%-3,041.67%
Worst 3-Month Return--
Time to Recovery (Days)10
5th Percentile Tail Loss-0.4%-0.41%
Time Underwater (Days)51
Percent Positive Months100.00.0
Avg. Up Month--
Avg. Down Month--
Win Days6.00.0
Loss Days6.012.0
Win Days%50.0%0.0%
Win Month%100.0%0.0%
Win Quarter%100.0%0.0%
Win Year%100.0%0.0%
Beta--0.16
Alpha--0.25
Correlation--20.38%
Treynor Ratio-27.84%
EOY Returns vs Benchmark
YearSPYStrategyMultiplierWon
20260.66-0.92-1.39-
Worst 10 Drawdowns
StartedRecoveredDrawdownDays
2026-01-152026-01-15-0.921
2026-09-29T23:15:01.477038
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:01.540298
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:01.617931
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:01.705163
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:01.769039
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:01.825147
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:01.880897
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:02.073813
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:02.164028
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:02.264273
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:02.322035
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:02.397842
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:15:02.463375
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['GOOGL', 'CMG', 'HLT', 'QSR', 'UBER', 'CP', 'LOW', 'MDLZ', 'BKNG', 'MSFT']
agent_max_model_calls160
agent_researcher_modelopenai/gpt-6-luna
agent_short_seller_modelopenai/gpt-6-luna
agent_trader_modelopenai/gpt-6-luna
agent_model_calls27
agent_researcher_calls9
agent_researcher_cache_hits0
agent_researcher_tool_calls239
agent_researcher_input_tokens1171614
agent_researcher_output_tokens39849
agent_researcher_total_tokens1211463
agent_researcher_thinking_tokens23686
agent_researcher_cached_input_tokens891498
agent_researcher_cache_write_input_tokens0
agent_researcher_uncached_input_tokens280116
agent_researcher_tool_use_input_tokens0
agent_researcher_latency_ms_total384733
agent_researcher_latency_ms_avg42748.11
agent_researcher_first_event_latency_ms_avg2741.67
agent_researcher_detail_parquetlogs/ackman-plain_2026-09-29_22-55_rrk4AI_agent_detail.parquet
agent_short_seller_calls9
agent_short_seller_cache_hits0
agent_short_seller_tool_calls190
agent_short_seller_input_tokens1167586
agent_short_seller_output_tokens33829
agent_short_seller_total_tokens1201415
agent_short_seller_thinking_tokens16767
agent_short_seller_cached_input_tokens972681
agent_short_seller_cache_write_input_tokens0
agent_short_seller_uncached_input_tokens194905
agent_short_seller_tool_use_input_tokens0
agent_short_seller_latency_ms_total365917
agent_short_seller_latency_ms_avg40657.44
agent_short_seller_first_event_latency_ms_avg3974.89
agent_short_seller_detail_parquetlogs/ackman-plain_2026-09-29_22-55_rrk4AI_agent_detail.parquet
agent_trader_calls9
agent_trader_cache_hits0
agent_trader_tool_calls153
agent_trader_input_tokens1620081
agent_trader_output_tokens35361
agent_trader_total_tokens1655442
agent_trader_thinking_tokens26237
agent_trader_cached_input_tokens1513131
agent_trader_cache_write_input_tokens0
agent_trader_uncached_input_tokens106950
agent_trader_tool_use_input_tokens0
agent_trader_latency_ms_total391012
agent_trader_latency_ms_avg43445.78
agent_trader_first_event_latency_ms_avg4406.33
agent_trader_detail_parquetlogs/ackman-plain_2026-09-29_22-55_rrk4AI_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.