Interpreting a Short News Sentiment Strategy Backtest Tear Sheet
Document Lumibot
Summary
This document presents a QuantStats tear sheet for a strategy labeled news-sentiment-generic, compared with SPY over January 4–15, 2026. It reports a 1% total return for both, while the strategy has higher annualized return and volatility, a lower Sharpe ratio, and a larger maximum drawdown. Its reported correlation to the benchmark is negative, and the table also includes risk, tail-loss, time-in-market, and drawdown statistics.
The material is useful as an example of how to read a backtest report and compare return with risk, rather than as an explanation of how to construct a sentiment signal. No news inputs, trade rules, asset selection process, or execution assumptions are described. The displayed period is very short, so annualized figures and other performance statistics should not be treated as reliable evidence of durable returns. The report itself cautions that past performance does not predict future results.
Key ideas
- The tear sheet compares a news sentiment strategy with SPY over a short January 2026 period.
- The strategy and benchmark each show a 1% total return in the report.
- The strategy has higher reported volatility and maximum drawdown, alongside a lower Sharpe ratio than SPY.
- The report gives no details about sentiment inputs, signal rules, or trade execution.
- The short sample limits the value of annualized performance and risk statistics.
Tags
Full text
# news sentiment ai trading bot
Tearsheet (generated by QuantStats)
news-sentiment-generic Compared to SPY 4 Jan, 2026 - 15 Jan, 2026
Benchmark is SPY | LumiBot 4.6.3 | DataSource yahoo | Backtest time 10:00 | Generated by QuantStats (Lumiwealth Version) (v.1.1.5)
Annual Return ⓘ
33.95%
Total Return ⓘ
1%
Max Drawdown ⓘ
-2.18%
RoMaD ⓘ
15.59
Longest DD Days ⓘ
5
Sharpe ⓘ
1.07
Sortino ⓘ
1.88
Key Performance Metrics
MetricSPYStrategy
Risk-Free Rate3.56%3.56%
Time in Market67.0%75.0%
Total Return1%1%
CAGR% (Annual Return)24.3%33.95%
Sharpe2.591.07
RoMaD35.1915.59
Corr to Benchmark1.0-0.16
Prob. Sharpe Ratio67.18%53.74%
Smart Sharpe2.431.0
Sortino4.731.88
Smart Sortino4.441.76
Sortino/√23.351.33
Smart Sortino/√23.141.25
Omega1.51.18
Max Drawdown-0.69%-2.18%
Longest DD Days35
Volatility (ann.)6.41%24.42%
R^20.020.02
Information Ratio0.020.02
Calmar35.1915.59
Skew0.450.65
Kurtosis0.140.15
Expected Daily%0.05%0.07%
Expected Monthly%0.66%0.88%
Expected Yearly%0.66%0.88%
Daily Value-at-Risk-0.5%-2.02%
Expected Shortfall (cVaR)-0.5%-2.02%
MTD0.66%0.88%
3M0.66%0.88%
6M0.66%0.88%
YTD0.66%0.88%
1Y0.66%0.88%
3Y (ann.)24.3%33.95%
5Y (ann.)24.3%33.95%
10Y (ann.)24.3%33.95%
All-time (ann.)24.3%33.95%
Best Day0.66%2.64%
Worst Day-0.49%-1.69%
Best Month0.66%0.88%
Worst 1-Month Return0.66%0.88%
Best Year0.66%0.88%
Worst Year0.66%0.88%
Avg. Drawdown-0.51%-1.59%
Avg. Drawdown Days23
Recovery Factor0.960.45
Ulcer Index0.00.01
Serenity Index-4.9-1.51
Annualized Return on Risk Capital2,895.24%1,235.09%
Worst 3-Month Return--
Time to Recovery (Days)10
5th Percentile Tail Loss-0.4%-1.63%
Time Underwater (Days)59
Percent Positive Months100.0100.0
Avg. Up Month0.66%0.88%
Avg. Down Month--
Win Days6.04.0
Loss Days6.08.0
Win Days%50.0%33.33%
Win Month%100.0%100.0%
Win Quarter%100.0%100.0%
Win Year%100.0%100.0%
Beta--0.6
Alpha-0.42
Correlation--15.73%
Treynor Ratio-4.46%
EOY Returns vs Benchmark
YearSPYStrategyMultiplierWon
20260.660.881.35+
Worst 10 Drawdowns
StartedRecoveredDrawdownDays
2026-01-142026-01-15-2.182
2026-01-052026-01-06-1.692
2026-01-082026-01-12-0.895
2026-09-29T23:25:05.957652
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.000960
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.041598
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.096782
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.142016
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.189417
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.241933
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.294213
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.343976
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.390346
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.429616
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.478145
image/svg+xml
Matplotlib v3.10.9, https://matplotlib.org/
2026-09-29T23:25:06.526943
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_calls184
agent_trader_input_tokens2752411
agent_trader_output_tokens40960
agent_trader_total_tokens2793371
agent_trader_thinking_tokens29292
agent_trader_cached_input_tokens2616316
agent_trader_cache_write_input_tokens0
agent_trader_uncached_input_tokens136095
agent_trader_tool_use_input_tokens0
agent_trader_latency_ms_total599259
agent_trader_latency_ms_avg66584.33
agent_trader_first_event_latency_ms_avg2886.67
agent_trader_detail_parquetlogs/news-sentiment-generic_2026-09-29_23-15_4pDSl0_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.