Stats

A trading strategy was tested on the stocks WCC, HUBB, and SPY from 2022 to 2025. The strategy, called Preregister1385, used a 20-day lookback period and held positions for 5 days. It entered a trade when the close price was higher than the prior rolling high and the 50-day simple moving average, and exited 5 trading sessions later. The strategy did not allow overlapping trades or trades that crossed into a new year. A fee of 0.1% and slippage of 0.1% were applied to each trade. The strategy was tested with all cash between positions, and the returns were compounded. The results showed a return of -43.22% and a drawdown of 45.60%. The strategy had a win rate of 46.55% and an average win of 2.55%. A news scan found the source of the data at https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The strategy was tested with a sensitivity analysis, which means it was tested with different parameters to see how it performed, and the results showed that the 20/5 parameters were unchanged despite ranking, but this is not evidence of how the strategy will perform in the future.

A training-only period from 2022 to 2025 was used to test a trading strategy for HUBB, with a lookback period of 20 days and a hold period of 3 days. The strategy was to enter a trade at the next open if the close was greater than the prior rolling high and the 50-day Simple Moving Average, and to exit the trade at the open 3 sessions later. No overlapping trades and no cross-year trades were allowed. A fee of 0.1% and slippage of 0.1% were applied to each side of the trade. All cash was reinvested between positions, with compounding applied to the full notional value per name, not account allocation. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The exact metrics of the strategy were: lookback of 20 days, hold of 3 days, return of -48.87%, drawdown of 49.43%, 71 samples, win rate of 32.39%, average win of 1.90%, average loss of 2.25%, and mean of -0.90%. The manual compounded cash return matched the results. The ranking was frozen on 20/5, but this is a test of training sensitivity, not evidence from a holdout period.

A training program for HUBB, which is a stock ticker, was run from 2022 to 2025 with a lookback period of 10 days, meaning it looked at the last 10 days of data, and a hold period of 10 days, meaning it held each position for 10 days. The program entered a position when the close price was higher than the prior rolling high and the 50-day simple moving average, or SMA50, which is a type of average stock price. It exited the position at the open price 10 hours later, with no overlapping trades and no trades that crossed into a new year. The program used a SIP adjustment, which refers to a type of data adjustment, and accounted for a 0.1% fee and 0.1% slippage, which is the difference between the expected and actual price of a trade, on each side of the trade. The program also used all cash between positions, compounded the full notional value, which is the total value of the investment, per name, but not per account allocation. The data came from a source at https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The exact metrics from the training program were: a lookback period of 10 days, a hold period of 10 days, a return percentage of -18.477481231956208, a drawdown percentage of 31.933645441298108, 45 samples, a win rate percentage of 53.333333333333336, an average win percentage of 4.107235130506873, an average loss percentage of 5.290730553172541, and a mean percentage of -0.27848218854352047. The manual compounded cash matched the results. The Frozen20/5, which is a type of ranking, remained unchanged despite the results, but this is only a measure of training sensitivity, not evidence of how the program will perform in the future.

A training session for HUBB was conducted from 2022 to 2025 with a lookback period of 10 days and a hold period of 5 days. The strategy was to enter a position at the next open if the close was higher than the prior rolling high and the 50-day Simple Moving Average, and to exit at the open 5 sessions later. The session had no overlap and did not cross years. The SIP adjustment was applied to all data, and a 0.1% fee and 0.1% slippage were applied to each side of the trade. All cash was reinvested between positions, with compounding applied to the full notional value per name, not account allocation. The data source was https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The metrics from this training session were: lookback of 10 days, hold of 5 days, return of -53.89%, drawdown of 56.56%, 65 samples, win rate of 41.54%, average win of 2.35%, average loss of 3.57%, and mean of -1.11%. The manual compounded cash matched the results. The Frozen20/5 strategy remained unchanged despite ranking, as this was a training sensitivity test, not a holdout evidence test.

A training session for HUBB was conducted on 10/3, with a cost analysis. The training parameters were set as follows: training-only from 2022 to 2025, with a lookback period of 10 days and a hold period of 3 days. The strategy was to enter a position at the next open if the close was higher than the prior rolling high and the 50-day Simple Moving Average, and to exit at the open 3 sessions later. The parameters also included no overlap and no cross-year trades. The Securities Information Processor adjustment was applied to all data. A fee of 0.1% and slippage of 0.1% were applied to each side of the trade. The cash was fully reinvested between positions, with compounding applied to the full notional value per name, not account allocation. The data source was https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The exact metrics were: lookback of 10 days, hold of 3 days, return percentage of -60.056162961544146, drawdown percentage of 62.01930908350705, sample size of 78, win rate percentage of 34.61538461538461, average win percentage of 1.711035792699132, average loss percentage of 2.6249080677131817, and mean percentage of -1.1240044237243034. The manual compounded cash matched the results. The parameters from 20/5 were left unchanged, despite ranking, as this was a training sensitivity test, not a holdout evidence test.

A news scan found the headline about WCC 2026 ablation_no_sma: frozen 20/5 electrical breakout. This refers to a type of stock trading strategy, where ablation_no_sma means a test without a Simple Moving Average, a calculation to smooth out price data. The strategy was tested from 2026 to September 8, with a fixed rule to buy when the stock's closing high price was above its 50-day average, and to sell after holding for 5 sessions. The test did not include any changes to the rule, and it included costs of 0.1% fee plus 0.1% slippage, which is the difference between expected and actual trade prices, on each side of the trade. The test also included a daily adjustment for the Securities Information Processor, which is a system that collects and distributes stock trade data. The results were verified using manual compounding, a way of calculating returns, and vectorbt, a trading strategy testing tool. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The test results were: return of 1.9043745633779146%, drawdown of 14.148690231859074%, sample size of 9, win rate of 55.55555555555556%, average win of 3.03986500607782%, average loss of 3.1617975764482553%, and mean of 0.2835705249551198%. The baseline trade dates and returns were: January 14 to 22, 2026, January 29 to February 5, 2026, February 9 to 17, 2026, April 9 to 16, 2026, April 20 to 27, 2026, May 1 to 8, 2026, May 12 to 19, 2026, May 27 to June 3, 2026, and August 3 to 10, 2026, with returns of 0.04054654709680072, 0.004249067602338341, -0.0369323067239169, 0.04247766240800499, -0.00483861093495408, 0.006680007668730781, -0.06889923281045973, -0.015801752588599505, and 0.07055747329566597. The 95% bootstrap mean confidence interval was -2.1918036650942527 to 3.061479355934164%, with a sample size of 9, and no event causal identification or 15-minute routing was used. The training rule was frozen and deeply negative, and there was no approval despite a positive point estimate.

A news scan found the headline about WCC 2026 stress with a frozen 20/5 electrical breakout. The trading strategy, called Preregister1385, was used from 2026 to September 8, with a fixed rule to close a position at the high of the last 20 days or the 50-day Simple Moving Average, which is a calculation to find the average price of a stock over a certain period. The position was held for 5 sessions and then exited at the open, with no overlap. The costs included a fee of 0.1% plus slippage of 0.3% on each side, which refers to the difference between the expected price and the actual price of a trade. The Systematic Investment Plan, or SIP, adjustment was made daily, and the vectorbt manual compounding was verified, which means that the interest was calculated and added to the principal at regular intervals. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The results showed a return percentage of -0.5359649712356804, a drawdown percentage of 16.184601826214973, a sample size of 9, a win rate percentage of 55.55555555555556, an average win percentage of 2.8778777386184373, an average loss percentage of 3.5483783842692462, and a mean percentage of 0.0217639062239113. The baseline trade dates and returns were from January 14, 2026, to August 10, 2026, with returns ranging from -0.06889923281045973 to 0.07055747329566597. The 95% bootstrap mean confidence interval was between -2.1918036650942527 and 3.061479355934164, with a sample size of 9 and no event causal identification or 15-minute routing. The training rule was frozen and deeply negative, with no approval despite a positive point estimate.

A news scan found the headline about WCC 2026 holdout with a frozen 20/5 electrical breakout. The trading strategy, called a breakout, is when a stock's price moves outside a certain range, in this case, 20 and 5, referring to the number of days for the short and long term moving averages, which are averages of the stock's price over a certain period of time. The strategy was tested from January 2026 to September 8, 2026, with a fixed rule to sell after 5 sessions if the stock's price was higher than its average price over 50 days, and to buy at the next opening price. The costs included a fee of 0.1% and slippage of 0.1% on each side, which is the difference between the expected price and the actual price of a trade. The data was adjusted daily using a system called SIP, which stands for Securities Information Processor, and the results were verified using a tool called vectorbt with manual compounding, which means that the returns were calculated and added to the principal amount at regular intervals. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The results showed a return of 3.11%, a drawdown of 14.15%, and a win rate of 55.56%. The baseline trade dates and returns were from January 14, 2026, to August 10, 2026, with returns ranging from -0.0689 to 0.0706. The 95% bootstrap mean confidence interval was between -2.19% and 3.06%. The training rule was frozen and deeply negative, and despite a positive point estimate, there was no approval.

A trading fund manager used a training setup from 2022 to 2025 with a 40-day lookback period and a 10-day hold period. The rules were to enter a trade at the next open if the close was higher than the prior rolling high and the 50-day simple moving average, and to exit 10 hours later. The manager did not allow overlapping trades or trades that crossed years. A small fee of 0.1% and slippage of 0.1% were applied to each side of the trade. All cash was reinvested between positions, with full notional value compounded per name, not per account allocation. The manager used data from a source that provides stock bars, specifically for the symbols WCC, HUBB, and SPY, with a one-day timeframe and all adjustments. The exact metrics from this training were a return of -65.23%, a drawdown of 69.84%, and a win rate of 44.83%. The average win was 5.40% and the average loss was 9.84%. The mean return was -3.01%. The manager noted that the manual compounded cash matched the results and that the frozen 20/5 setup remained unchanged, despite ranking, as this was a training sensitivity test, not a holdout evidence test.

A training-only period from 2022 to 2025 was used for WCC, with a lookback period of 40 days and a hold period of 5 days. The trading rule was to enter a position at the next open if the close was higher than the prior rolling high and the 50-day simple moving average, and to exit at the open 5 days later. No overlapping trades and no trades that cross years were allowed. A fee of 0.1% and slippage of 0.1% were applied to each side of the trade. All cash was reinvested between positions, with compounding applied to the full notional value per name, not account allocation. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The exact metrics for this training period were: lookback of 40 days, hold of 5 days, return of -40.51534305580721%, drawdown of 45.17591328612437%, 36 samples, win rate of 52.77777777777778%, average win of 3.5412224033743422%, average loss of 6.541450876641782%, and mean of -1.2200399788554936%. The manual compounded cash matched these results. A frozen 20/5 period remained unchanged despite ranking, as this is a test of training sensitivity, not holdout evidence.

A training program for WCC, which is a stock ticker, was set up from 2022 to 2025 with a 40-day lookback period, meaning it looks at the last 40 days of data, and a 3-day hold period, meaning it holds a position for 3 days. The program enters a position at the next open if the close is greater than the prior rolling high and the 50-day Simple Moving Average, or SMA, which is a calculation of the average price over 50 days. It exits the position 3 sessions later. The program does not allow overlapping trades or trades that cross years. It also adjusts for the Securities Information Processor, or SIP, which is a system that collects and disseminates market data. The program includes a 0.1% fee and 0.1% slippage, which is the difference between the expected and actual price of a trade, on each side of the trade. All cash is reinvested between positions, with the return compounded, or added to, the initial investment. The data comes from a source at https://runway.adityaperswal.workers.dev/data/stock-bars, which provides stock market data. The exact metrics of the program are: a 40-day lookback period, a 3-day hold period, a return of -49.69990360078144%, a drawdown of 51.63678902335472%, 43 samples, a win rate of 53.48837209302325%, an average win of 2.160598523807327%, an average loss of 5.502937579538042%, and a mean return of -1.4038368730974955%. The manual return was -49.69990360078137%, which matches the compounded cash. The Frozen20/5, which is a ranking system, remained unchanged despite the results, but this is only a test of the program's sensitivity, not a prediction of its future performance.

A training-only period from 2022 to 2025 was used for WCC, with a lookback period of 20 days and a hold period of 10 days. The trading rule was to enter a position at the next open if the close was greater than the prior rolling high and the 50-day Simple Moving Average, and to exit at the open 10 sessions later. No overlapping trades and no cross-year trades were allowed. A fee of 0.1% and slippage of 0.1% were applied to each side of the trade. All cash was reinvested between positions, with compounding applied to the full notional value per name, not account allocation. The data source was https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The metrics for this training period were: lookback of 20 days, hold of 10 days, return of -60.21%, drawdown of 67.13%, 36 samples, win rate of 44.44%, average win of 6.70%, average loss of 8.96%, and mean of -2.00%. The manual compounded cash return matched the calculated return. The Frozen20/5 ranking remained unchanged, which is a measure of training sensitivity, not holdout evidence.

A training-only period from 2022 to 2025 for WCC used a lookback of 20 days and a hold of 5 days. The strategy was to close a position when its price was higher than the prior rolling high and the 50-day Simple Moving Average, and to enter a new position at the next open, exiting after a certain number of hours later. The training had no overlapping trades and no trades that crossed years. A fee of 0.1% and slippage of 0.1% were applied to each side of the trade. All cash was held between positions, with compounding applied to the full notional value per name, not account allocation. A news scan found the source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The exact metrics were: lookback of 20 days, hold of 5 days, return percentage of -37.55373038338062, drawdown percentage of 45.21697039970043, sample size of 47, win rate percentage of 51.06382978723404, average win percentage of 3.9084366244948883, average loss percentage of 5.710621567648203, and mean percentage of -0.7987620652772625. The manual compounded cash matched the results. The 20/5 strategy remained unchanged despite ranking, as this is a test of training sensitivity, not holdout evidence.

A training session for WCC was conducted on 20/3, with costs considered. The training parameters were set as follows: training from 2022 to 2025, looking back 20 days, and holding for 3 days. The strategy was to close a position if its price was higher than the prior rolling high and the 50-day Simple Moving Average, which is a calculation of the average price over 50 days. A new position would be entered at the next open, and exited after 3 sessions. There were no overlapping trades and no trades that crossed into a new year. The Securities Information Processor, or SIP, which is a system that collects and disseminates market data, was used to adjust all data. The vectorbt fee, which is a fee for using the vectorbt platform, was set at 0.1%, and slippage, which is the difference between the expected and actual price of a trade, was also set at 0.1% for each side of the trade. All cash was reinvested between positions, with the full notional value compounded per name, but not per account allocation. The data source was https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The exact metrics from the training session were: lookback of 20 days, hold of 3 days, return percentage of -58.344601017836254, drawdown percentage of 59.948608581155405, 56 samples, win rate percentage of 50, average win percentage of 2.6298076948016464, average loss percentage of 5.360106346303362, and mean percentage of -1.3651493257508576. The manual return percentage was also -58.344601017836226, and the compounded cash matched. The parameters from 20/5 were left unchanged, despite ranking, as this was a test of training sensitivity, not a holdout evidence test.

The WCC training had a sensitivity of 10 out of 10 and was costed. The training was done from 2022 to 2025 with a lookback period of 10 days and a hold period of 10 days. The strategy was to enter a position at the next open if the close was greater than the prior rolling high and the 50-day Simple Moving Average, and to exit the position after a certain number of hours. The training did not allow for overlapping trades or trades that crossed years. A fee of 0.1% and slippage of 0.1% were applied to each side of the trade. The training was done with all cash between positions, and the returns were compounded on a full notional basis per name, not on an account allocation basis. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The exact metrics of the training are: lookback of 10 days, hold of 10 days, return percentage of -57.02468745017117, drawdown percentage of 68.97589349151562, sample size of 43, win rate percentage of 41.86046511627907, average win percentage of 6.904531447473363, average loss percentage of 7.604555314343145, and mean percentage of -1.530984111722282. The manual compounded cash matched the training results. The ranking of Frozen20/5 remained unchanged at 20/5, but this is a measure of training sensitivity, not holdout evidence.

A training session for WCC was conducted from 2022 to 2025 with a lookback period of 10 days and a hold period of 5 days. The strategy was to enter a trade at the next open if the close was higher than the prior rolling high and the 50-day Simple Moving Average, and to exit the trade 5 hours later. The session used a preregistered training set of 1385, with no overlapping trades and no trades that crossed years. A fee of 0.1% and slippage of 0.1% were applied to each side of the trade. The results were calculated using all cash between positions, with compounding applied to the full notional value per name, not account allocation. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The metrics from the training session were: lookback of 10, hold of 5, return of -40.57815190900065%, drawdown of 45.624296974993726%, 55 samples, win rate of 49.09090909090909%, average win of 4.108344773287125%, average loss of 5.431874562324664%, and mean of -0.7484941612061498%. The manual compounded cash matched the results. The Frozen20/5 was unchanged despite ranking, as this is a training sensitivity test, not a holdout evidence test.

A preregistered training for WCC from 2022 to 2025 used a lookback period of 10 days and a hold period of 3 days. The training rule was to enter a position at the next open if the close was greater than the prior rolling high and the 50-day Simple Moving Average, and to exit at the open 3 sessions later. The training did not allow overlapping trades or trades that crossed years. A Securities Information Processor adjustment was applied to all data. The backtest used a 0.1% fee and 0.1% slippage on each side of the trade. The cash was fully reinvested between positions, with compounding applied to the full notional value per stock name, not account allocation. The data source was https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=WCC,HUBB,SPY&timeframe=1Day&feed=sip&adjustment=all. The training metrics were: lookback of 10 days, hold of 3 days, return of -64.45%, drawdown of 65.82%, 65 samples, win rate of 49.23%, average win of 2.72%, average loss of 5.38%, and mean return of -1.39%. The manual compounded cash return matched the backtest. The frozen date of 20/5 remained unchanged despite ranking, as this is a training sensitivity test, not a holdout evidence test.

A diagnostic test was run on the SRRK stock using a momentum trading strategy with the following parameters: momentum20, stop5%, target10%, and days730 on the IEX exchange. The test was then repeated with the same strategy, but with a holdout period from 2026 through September 8, and 20 prior bars for warmup. The results of the holdout period were: fund catalyst, split holdout, symbol SRRK, 191 bars, return percentage -28.08145949402554, buy and hold percentage 31.96966214663297, max drawdown percentage 34.1333589954249, win rate 16.666666666666664, average trade percentage -1.800182191174515, and 18 trades. The test showed that the strategy's execution model is not suitable for FDA gaps, as it assumes zero fees and slippage, and same-close signal entry and stop fills at the exact stop even if the price gaps below it. This is contradicted by the actual ledger and 15-minute gap audit. The results cannot be trusted, and no parameter was selected for live use. The buy-and-hold results include the warmup period and should not be used as aligned holdout excess return. The data source is https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all, with raw and split observations 17369-78 and 17387-91. The independent costed vectorbt calendar tests answer the question, but this diagnostic test does not supply position size.

A diagnostic test was run on the TLX stock using a momentum strategy with the following settings: 20-day momentum, 5% stop loss, 10% target, and 730 days of data from the IEX exchange. The test was then repeated with the same strategy, but this time using data from 2025 for training and 2026 up to September 8 for testing, with 20 prior days for warm-up and no trading during the warm-up period. The results of the test were: the fund, called catalyst, had a return of 14.65%, the stock had a return of 24.02% if bought and held, the maximum loss was 18.64%, 40% of trades were winners, and the average trade return was 0.84%. The test showed that the strategy did not account for fees or slippage, and that it treated stop losses in a way that is not realistic, as it assumed that stops would be filled at the exact stop price even if the price gapped below it. This is not how stops work in real life, as shown by the actual ledger of RARE and an audit of 15-minute gaps. Because of this, the positive results of the test cannot be trusted, and no parameters were chosen for live use. The buy-and-hold return includes the warm-up period and should not be used to compare to the strategy's return. The data used for the test came from https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all, and the test was also checked with other data and tests, including a costed vectorbt calendar test.

A diagnostic test was run on the MIRM stock using the CLI momentum strategy with the following parameters: momentum20, stop5%, target10%, and days730 on the IEX exchange. The test was then repeated with the same engine and strategy, but this time with a holdout period from 2026 to September 8, using the previous 20 bars for warmup and flat warmup trading. The results of the holdout period were: fund catalyst, symbol MIRM, 191 bars, return percentage 22.16509767375947, buy and hold percentage 40.20284547119313, maximum drawdown percentage 15.199708089039069, win rate 50, average trade percentage 1.5664072813636993, and the total number of trades was 16. However, an inspection of the engine code revealed that it does not account for fees or slippage, and it uses a same-close signal entry and stop fills at the exact stop price, even if the price gaps below it. This is contradicted by the actual ledger and a 15-minute gap audit. As a result, the positive gross results cannot be trusted, and no parameters were selected for live use. The buy-and-hold percentage includes the warmup period and should not be used to calculate the excess return. The data was sourced from https://runway.adityaperswal.workers.dev/data/stock-bars, and additional tests were run using the vectorbt calendar with exposure audit to answer questions about the strategy.

A diagnostic test was run on the IONS stock using a momentum strategy with specific parameters: momentum20, stop5%, target10%, and days730. The test was done on a dataset from IEX and then the same strategy was applied to a different dataset for training until 2025 and for testing from 2026 until September 8. The test results showed a return of -14.070477285394468% for the strategy, compared to -30.70625610948192% for a buy-and-hold approach. The strategy had a maximum drawdown of 18.321309831926% and a win rate of 31.25%. The average trade return was -0.8359489928864545%. The test was done with 20 prior bars for warmup and flat warmup trading, and a total of 191 bars were used for the holdout test. The results also showed that the strategy had 16 trades. An inspection of the code showed that it did not account for fees or slippage, and that stop losses were filled at the exact stop price even if the price gapped below it. However, this is not consistent with actual trading data, which showed gaps in prices. Therefore, the positive results of the test cannot be trusted, and no parameters were selected for live use. The buy-and-hold return includes the warmup period and should not be used to calculate the excess return of the strategy. The data used for the test came from https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all. Additional tests were done using a costed vectorbt calendar, but this diagnostic test did not provide information on position size.

A diagnostic test was run on the CLI momentum strategy with the following parameters: momentum20, stop5%, target10%, and days730 on the IEX exchange. The test was then imported and run on a different dataset, with a holdout period from 2026 to September 8, and 20 prior bars for warmup. The results of the holdout period for the symbol RARE were as follows: 191 bars, return percentage of 1.8975920520518441%, buy and hold return percentage of -59.17695473251029%, maximum drawdown percentage of 22.621906250000023%, win rate of 33.33333333333333%, average trade percentage of 0.3544089355959463%, and 15 trades. The test showed that the strategy's execution model is not suitable for stocks like RARE that experience large price gaps, as it does not account for fees or slippage and fills stops at the exact stop price even if the price gaps below it. This is contradicted by RARE's actual trading ledger and a 15-minute gap audit. The results of the test cannot be trusted, and no parameters were selected for live use. The test data was sourced from https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all, and additional tests were run using vectorbt calendar tests with exposure audit.

A diagnostic test was run on the stock symbol APD using a computer program. The test used a strategy called breakout, which is a way of deciding when to buy or sell a stock based on its price movements. The test looked at 20 days of price history and ran for 730 days. It used a stop loss of 3 percent and a target profit of 6 percent. The data for the test came from a website called https://runway.adityaperswal.workers.dev/data/stock-bars. The test found 501 times when the stock price closed at the same level on different exchanges, but the signals to buy or sell were different. The test did not take into account the costs of buying and selling, or the time of day when trades were made. The results of the test should not be compared to other tests that use a different method. The test found that the stock APD had a return of 1.799 percent, which is less than the 8.727 percent return of just buying and holding the stock. The stock had a maximum loss of 9.926 percent and a win rate of 35.294 percent, which means that 35.294 percent of the trades made a profit. The average profit per trade was 0.067 percent. The test used 34 samples of data. The test also used a qualification period from 1454 to 1459, which means that the test looked at data from those years to decide if the strategy was working. The test did not result in any orders to buy or sell the stock.

A diagnostic test was run on the LIN stock using a computer program called node and a script called backtest.js. The test used the breakout strategy and looked at 20 days of data over a period of 730 days. The test stopped when the stock price fell by 3 percent and targeted a 6 percent increase. The data came from a website called https://runway.adityaperswal.workers.dev/data/stock-bars. The test found 501 times when the stock closed at the same price on the same day, but had different signals to sell. The test did not account for costs and the time it takes to buy or sell stocks. The results should not be compared to other tests that use a different method. The test results showed that the stock LIN had a return of -1.1607 percent, while simply buying and holding the stock would have given a return of 1.0795 percent. The stock's price fell by as much as 8.7524 percent at one point. The test made 36 trades, with 36.1111 percent of them being winning trades, and the average trade resulted in a loss of 0.0226 percent. The test used a sample of 36 trades. The qualification period from 1454 to 1459 was used to evaluate the test, and it rejected the results. No orders to buy or sell stocks were made.

A preregistered note, numbered 1339, was implemented on 1347, before the price outcomes were known. The term T10_T2 refers to the tenth trading session of the second trading period, which is strictly before the issuer's goal. The strategy involves buying at the open and selling at the close, with goals retained on weekends. Ten completed decisions were selected across six issuers, but this is not a complete FDA denominator. Three decisions, MIRM chenodiol 2025, RARE UX111 2025, and NUVL 2026, were resolved before entry and were skipped. The remaining decisions for 2025 include N5, 3TLX, IONS, and SRRK, while the 2026 decisions include IONS olezarsen and RARE DTX401. Advance notices were verified, including the February 23 DTX401 notice. The vectorbt separate event sleeves had equal initial cash, and the portfolio was the sum of the values with idle capital. Overlapping events were not falsely compounded. Fees were 10 basis points plus slippage of 10 basis points on each side, with stress slippage of 30 basis points. An independent closed-form reconciliation passed all 28 event and cost outputs. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all. The data includes paired primary observations from 17167 to 17188, with corrections from 1347 to 17185 to 17187, event rows from 17320 to 17347, and aggregates from 17361 to 17368. The training results for 2025 were: rule T10_T2, year 2025, slippage 0.001, N 5, return percentage 6.5375, drawdown percentage 2.0721, win rate percentage 80, average win percentage 8.9218, average loss percentage 2.9999, mean percentage 6.5375, and confidence interval 0.7997 to 13.2814. The holdout results for 2026 were: rule T10_T2, year 2026, slippage 0.001, N 2, return percentage 3.6779, drawdown percentage 3.0448, win rate percentage 50, average win percentage 10.0230, average loss percentage 2.6672, mean percentage 3.6779, and confidence interval -2.6672 to 10.0230. The stress holdout results for 2026 were: rule T10_T2, year 2026, slippage 0.003, N 2, return percentage 3.2640, drawdown percentage 3.1392, win rate percentage 50, average win percentage 9.5838, average loss percentage 3.0558, mean percentage 3.2640, and confidence interval -3.0558 to 9.5838. Both holdout windows crossed the actual early approval: IONS on June 24 at 14:37:29 ET before the June 26 exit, and RARE on August 19 at 17:22:01 ET before the August 20 exit. The positive 3.6779% return is not a pure pre-news edge, and the N2 bootstrap confidence interval -2.6672 to 10.0230 spans zero. The Gozelli training exit was on March 20, the same US date as the SEC acceptance at 17:34:54 ET, but the earliest FDA/ASX news minute is unresolved, so the exit is retained as ambiguous. No intraday stops or targets were simulated, and fees were assumed not to be venue-invoiced. Daily open and close execution is not guaranteed. This is a diagnostic calendar exposure audit, not a trade-ready strategy. There will be no retuning based on the holdout, and the operational allocation is 0.