notes.md

report.md

Important disclosure
This backtest is a hypothetical historical simulation and does not represent actual trading performance. Backtested results do not guarantee future results. Results depend on market-data quality, data feed selection, corporate-action handling, fees, slippage, liquidity, taxes, execution assumptions, and implementation details. This material is for research and educational purposes only and is not investment advice, a recommendation, an offer, or a solicitation to buy or sell securities, options, cryptocurrencies, or any other financial product. All investments involve risk and may lose value. Review Alpaca's disclosures and agreements at alpaca.markets/disclosures.

Paper trading is a simulated environment. It does not involve real money or actual securities transactions. Paper results may differ from live trading because of fill assumptions, market impact, liquidity, latency, data differences, order handling, fees, and other market conditions.

notes.md

summary.json

report.md

https://files.alpaca.markets/disclosures/library/BrokFeeSched.pdf

1. Gather required inputs: start date, end date, strategy concept or strategy file.
2. Gather or infer the rest: asset class, symbols or universe, timeframe, initial cash, position sizing, feed, adjustment mode, execution assumptions, benchmark.
3. Work through run considerations: order simulation, indicators, dividends, splits, fees, slippage, spread, market hours, calendar handling, and validation.
4. Translate your freeform idea into precise mathematical rules.
5. Present the formalized interpretation to you before writing code unless your request was already mathematically precise.
6. Check the workspace for reusable data, prior runs, and existing utilities.
7. Create a self-contained run folder.
8. Write

   notes.md

   ,

   strategy_spec.json

   ,

   config.json

   , and a readable run-specific script.
9. Fetch historical data through the Alpaca CLI, save raw CLI outputs, filter to the chosen market hours, and compute data fingerprints.
10. Run the local simulation.
11. Write artifacts.
12. Return the Teaching Five, first/last trade, assumptions, caveats, data fingerprint, and artifact paths.

run.py

fill_price = bar_open * (1 + friction_pct)

• read raw or normalized files from the run folder;
• implement the confirmed strategy exactly;
• implement the chosen indicator definitions exactly (see Indicator formulas);
• keep signal timing separate from fill timing;
• compute fees, slippage, spread, and settlement according to the confirmed assumptions;
• produce all required artifacts;
• include deterministic sorting and timezone handling;
• avoid hidden network calls after data fetch unless explicitly documented.

notes.md

• next_open

  (default): signal on bar T close; fill on bar T+1 open or quote at T+1 open timestamp.

• time_based

  : fill at a confirmed time of day; quote bid/ask when available.

• same_bar

  : only when explicitly requested; document look-ahead risk in

  notes.md

  and the report.
• Limit and stop orders: OHLC-bar eligibility rules apply; use conservative intrabar conflict policy when stop and target both touch the same bar.

1. total return versus benchmark;
2. max drawdown;
3. number of trades;
4. win rate;
5. Sharpe ratio versus benchmark.

• order simulation and fill timing;
• quote-aware versus bar-proxy fills;
• dividend handling;
• split and reverse-split handling;
• execution friction;
• PDF-derived trading-activity fees;
• market hours and extended-hours inclusion;
• calendar-based decisions;
• benchmark choice;
• look-ahead bias;
• survivorship bias;
• out-of-sample or walk-forward validation for parameter tuning;
• overfitting risk for repeated variants.

notes.md

• using future data in signal generation;
• using same-bar decision and fill without a documented

  same_bar

  model and warning;
• hiding execution assumptions;
• mixing adjusted bars with separate split adjustments;
• pretending vague rules were fully specified;
• discarding generated code after the run;
• including extended-hours bars unless you requested them;
• silently substituting indicator variants;
• treating open, close, high, low, VWAP, and quote-derived prices as interchangeable fill proxies;
• computing Sharpe from per-bar returns when the report says daily Sharpe;
• using population standard deviation for Sharpe when sample standard deviation (N-1) is required;
• submitting live orders as part of a historical backtest;
• claiming support for unsupported products — options require explicit contract selection and fill logic;
• bypassing the Alpaca CLI by switching to direct HTTP calls;
• running Alpaca CLI commands in a sandbox without local auth and filesystem access;
• implementing fill logic that deviates from Fill model rules without documenting the deviation in

  notes.md

  ;
• using

  close

  vs

  high

  vs

  low

  interchangeably for signal triggers;
• silently choosing between crossover and threshold signal logic;
• generating a multi-module engine when a single-file script will do.

• reference.md