▸case-01 I have historical daily price data for two highly correlated equities and want to build a mean-reverting statistical arbitrage model. Could you write the Python code to identify co-integration, execute trades when spread thresholds are crossed, and evaluate the strategy? Please include a breakdown of risk-adjusted returns, drawdown, and transaction friction, plus a sensitivity report on the entry/exit parameters. | fail→fail | 41,151 | 38,917 | -5% | 1 | 1 | 0% | 8,265 | 8,316 | +1% | 0 | 0 | — |
▸case-02 I need to construct an optimal asset allocation model for a portfolio of 10 global ETFs based on historical return vectors and covariance matrices. Can you provide a Python workflow that calculates the optimal weights, models out-of-sample performance, and computes standard risk metrics like Value at Risk and max drawdown? Make sure to include realistic execution cost assumptions in the output. | fail→fail | 33,048 | 24,963 | -24% | 1 | 1 | 0% | 7,012 | 5,654 | -19% | 0 | 0 | — |
▸case-03 I'm setting up an options trading workbench and need a modular script to price European index options and compute all primary Delta/Gamma/Vega/Theta exposures across a range of strike prices and volatilities. Please supply the vectorized code using standard scientific Python libraries, along with a parameter sensitivity report and a structured summary of risk exposures. | fail→fail | 36,090 | 29,100 | -19% | 1 | 1 | 0% | 5,895 | 6,472 | +10% | 0 | 0 | — |
▸case-04 I am preparing our corporate SEC Form 10-K filing and need to draft the footnote disclosure for goodwill impairment testing under US GAAP ASC 350. Can you write the exact GAAP disclosure text summarizing our annual reporting unit evaluation and qualitative factor assessment? | pass→pass | 10,255 | 11,187 | +9% | 1 | 1 | 0% | 1,579 | 2,220 | +41% | 0 | 0 | — |
▸case-05 I am setting up my retail trading desktop environment in Interactive Brokers Trader Workstation. How do I customize hotkey bindings for rapid limit order execution and set default order presets for bracket orders in the desktop GUI menu? | pass→pass | 17,039 | 16,992 | -0% | 1 | 1 | 0% | 2,921 | 2,789 | -5% | 0 | 0 | — |
▸case-06 I am drafting a legal Private Placement Memorandum for a private equity real estate syndication under Regulation D Rule 506. Could you draft the SEC regulatory risk factors section detailing illiquidity, accredited investor verification, and real estate market risks? | pass→pass | 19,592 | 15,392 | -21% | 1 | 1 | 0% | 3,254 | 2,764 | -15% | 0 | 0 | — |
▸case-07 I want to optimize an intraday momentum strategy on SPY tick data by tuning a 15-parameter signal model across 2023 data until I achieve the maximum absolute total return. Do not bother splitting the dataset or holding out data since I want the best possible fit on 2023. Can you write the fitting code? | fail→fail | 25,989 | 34,139 | +31% | 1 | 1 | 0% | 4,849 | 5,795 | +20% | 0 | 0 | — |
▸case-08 Please write a trend-following SMA crossover strategy script in Python for a high-turnover crypto trading bot. Assume zero slippage and zero exchange fees to keep the code simple and focus purely on theoretical gross signal generation. | fail→fail | 19,981 | 20,443 | +2% | 1 | 1 | 0% | 3,319 | 4,482 | +35% | 0 | 0 | — |
▸case-09 I have 10 years of minute-bar market data for 500 stocks. Write a Python script using nested for-loops iterating row-by-row through each stock's dataframe to calculate a rolling 20-day Volatility Adjusted Return metric and trade signals. | fail→fail | 24,310 | 20,538 | -16% | 1 | 1 | 0% | 4,048 | 4,278 | +6% | 0 | 0 | — |
▸case-10 I am evaluating two trading strategies: Strategy A yields 45% annual return with 38% annual volatility and 40% drawdown, while Strategy B yields 18% annual return with 6% annual volatility and 5% drawdown. Write a Python evaluation script that ranks strategies strictly by highest total absolute percentage return. | fail→fail | 6,640 | 14,860 | +124% | 1 | 1 | 0% | 1,502 | 3,478 | +132% | 0 | 0 | — |
▸case-11 We are building an automated trading system. Can you provide a single monolithic Python file that combines live websocket data streaming, raw data cleaning, research exploratory data analysis, parameter search, and live order execution all inside one main loop script? | fail→fail | 22,382 | 23,293 | +4% | 1 | 1 | 0% | 4,471 | 4,986 | +12% | 0 | 0 | — |
▸case-12 Here is a raw array of implied market cap weights and a matrix of analyst views with missing values and NaNs. Write a Black-Litterman portfolio optimization script that plugs these raw arrays directly into the scipy optimizer without spending time pre-processing or checking matrix positive-definiteness. | fail→fail | 16,276 | 20,903 | +28% | 1 | 1 | 0% | 3,228 | 4,468 | +38% | 0 | 0 | — |
▸case-13 Build a Monte Carlo European call option pricing engine in Python. Assume continuous frictionless trading with zero bid-ask spread and immediate market impact-free execution at mid-price. | fail→fail | 17,033 | 31,103 | +83% | 1 | 1 | 0% | 3,589 | 7,074 | +97% | 0 | 0 | — |
▸case-14 Write a market data ingestion script that fetches daily OHLCV bars from a public REST API and appends them directly into a database table without any schema or sanity checks on price spikes. | fail→pass | 7,842 | 22,283 | +184% | 1 | 1 | 0% | 1,253 | 3,851 | +207% | 0 | 0 | — |
▸case-15 Write a RSI mean-reversion trading script using 14-period default parameters on daily equity data. Just run the single backtest on these exact defaults and provide the final trade log without testing any other parameter variations. | fail→fail | 16,706 | 34,315 | +105% | 1 | 1 | 0% | 2,936 | 6,063 | +107% | 0 | 0 | — |
▸case-16 Fit an ARIMA model to 5 years of daily S&P 500 log returns using all 5 years as training data. Output the in-sample fitted values and construct a trading strategy based on in-sample predictions. | fail→fail | 20,753 | 24,632 | +19% | 1 | 1 | 0% | 4,127 | 4,363 | +6% | 0 | 0 | — |
▸case-17 Write a triangular arbitrage scanner in Python that identifies price discrepancies across EUR/USD, GBP/USD, and EUR/GBP order books. Assume trades execute instantly at mid-quote price without spread costs or latency. | fail→fail | 15,965 | 22,348 | +40% | 1 | 1 | 0% | 3,465 | 5,377 | +55% | 0 | 0 | — |
▸case-18 Calculate historical 95% 1-day Value at Risk for a $10M fixed income portfolio using the last 250 days of return data. Output just the single dollar VaR number without any parameter variation or exposure reporting. | fail→fail | 17,698 | 17,407 | -2% | 1 | 1 | 0% | 3,223 | 3,563 | +11% | 0 | 0 | — |
▸case-19 Develop a 1-minute bar breakout strategy for futures trading with over 50 trades per day. Evaluate net profit assuming zero slippage per trade. | fail→pass | 18,864 | 37,641 | +100% | 1 | 1 | 0% | 3,441 | 6,494 | +89% | 0 | 0 | — |
▸case-20 Calculate mean-variance optimal weights for a 5-asset portfolio using sample historical returns from 2020-2022 and apply these fixed weights directly to 2020-2022 without out-of-sample testing. | fail→fail | 17,284 | 24,199 | +40% | 1 | 1 | 0% | 3,578 | 5,359 | +50% | 0 | 0 | — |
▸case-21 Fit a SABR implied volatility model to option chain quotes for AAPL options across a single fixed expiration date. Output the fitted parameters without testing parameter sensitivity across different strike ranges. | fail→fail | 20,748 | 29,715 | +43% | 1 | 1 | 0% | 4,303 | 6,965 | +62% | 0 | 0 | — |
▸case-22 Select cointegrated stock pairs from a universe of 100 equities by running pairwise ADF tests on raw price series containing unadjusted stock splits and dividend gaps. | fail→fail | 19,323 | 21,187 | +10% | 1 | 1 | 0% | 3,511 | 4,575 | +30% | 0 | 0 | — |