Notes

A news scan found the headline 'Methods note3577'. This is a calculation from September 2018 using data from completed September 2017 bars. The results are given in percent units. Simulations are conditional and include a Kelly diagnostic, which is a measure of risk. The data includes the following information: split, lookback, filter, cost in basis points per side, number of bars, return percentage, closed return percentage, drawdown percentage, win rate percentage, number of trades, mean trade percentage, median trade percentage, open trades, buy and hold percentage, targets, and gaps. The results are as follows: a holdout with 10 lookback and sma50 filter had a return of 220.19 percent, a holdout with 10 lookback and sma50 filter and 16 cost had a return of 217.64 percent, a holdout with 20 lookback and sma50 filter had a return of 220.19 percent, a holdout with 20 lookback and sma50 filter and 16 cost had a return of 217.64 percent, a holdout with 40 lookback and sma50 filter had a return of 87.26 percent, a holdout with 40 lookback and sma50 filter and 16 cost had a return of 85.40 percent, a holdout with 20 lookback and no filter had a return of 44.45 percent, a holdout with 20 lookback and sma200 filter had a return of -12.98 percent, a holdout with 20 lookback and spy200 filter had a return of 25.11 percent, a forward 2026 with 10 lookback and sma50 filter had a return of -5.55 percent, a forward 2026 with 10 lookback and sma50 filter and 16 cost had a return of -6.39 percent, and a forward 2026 with 20 lookback and sma50 filter had a return of -10.25 percent. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=PSIX&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It said that a calculation was done in September 2018 using data from September 2017. The calculation used something called percent units, which are units of measurement that show a value as a percentage. The simulations, which are like practice runs, were conditional, meaning they depended on certain conditions being met. A Kelly diagnostic, which is a tool used to measure the performance of an investment strategy, was also used. The results of the calculation are shown in a table with the following columns: split, regime, above, n, mean percentage change, and win percentage change. The rows in the table show the following results: for the holdout period, the own200 regime had a mean percentage change of 34.83563014 and a win percentage change of 100, the spy200 regime had a mean percentage change of 28.10869167 and a win percentage change of 100 when the value was above a certain point, and a mean percentage change of 55.01644555 and a win percentage change of 100 when the value was not above that point. For the forward2026 period, the own200 regime had a mean percentage change of 10.20697194 and a win percentage change of 50 when the value was above a certain point, and a mean percentage change of -14.45234742 and a win percentage change of 0 when the value was not above that point. The spy200 regime had a mean percentage change of -2.12268774 and a win percentage change of 25. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=PSIX&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was made. It used a September 2018 calculation on completed September 2017 bars. The percent units were explicitly named. Simulations were conditional and used a Kelly diagnostic, which is a tool to measure risk. The results were as follows: the columns included split, n, mean percent, mean confidence interval 95 percent, win percent, average win percent, average loss percent, half Kelly stock fraction, half Kelly dollars, minimum trade percent, and maximum trade percent. The rows of data were for holdout and forward2026. For holdout, the results were: 4, 34.83563014 percent, a confidence interval of 17.09691476 to 49.86546556 percent, 100 percent win rate, 34.83563014 percent average win, 0 percent average loss, 0.5 half Kelly stock fraction, 101.99 half Kelly dollars, 9.23705483 percent minimum trade, and 55.01644555 percent maximum trade. For forward2026, the results were: 4, -2.12268774 percent, a confidence interval of -15.07828984 to 22.49847513 percent, 25 percent win rate, 34.78997832 percent average win, 14.42690975 percent average loss, 0 half Kelly stock fraction, 0 half Kelly dollars, -15.70423226 percent minimum trade, and 34.78997832 percent maximum trade. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=PSIX&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It is about a calculation done in September 2018 using data from September 2017. The calculation is about percent units and is based on certain conditions. It also includes a Kelly diagnostic, which is a way to measure how well a trading strategy is working. The results are shown in a table with the following information: the name of the simulation, the number of times it was run, the minimum gap percentage, the percentage of gaps that were one percent or less, the percentage of gaps that were zero point one percent or less, the number of times the price was below ten percent, twenty percent, and thirty percent, the minimum percentage change in the closing price, and the maximum percentage change in the closing price. The table has two rows of data: one for a holdout simulation and one for a forward 2026 simulation. The holdout simulation was run 253 times, with a minimum gap percentage of -29.99753816, a one percent gap percentage of -11.56645803, and a zero point one percent gap percentage of -26.54048412. The forward 2026 simulation was run 178 times, with a minimum gap percentage of -34.18734988, a one percent gap percentage of -8.29938242, and a zero point one percent gap percentage of -30.92071373. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=PSIX&timeframe=1Day&feed=sip&adjustment=all

A methods note, numbered 3577, was made on September 18, using data from completed bars on September 17. The calculation used percent units and explicitly named them. Simulations were conditional and included a Kelly diagnostic, which is a measure of risk. The data included the following information: date, number of items, close price, prior 20-day average, 50-day simple moving average, 200-day simple moving average, 20-day average true range, average true range as a percentage, 20-day realized volatility, 20-day average volume, signal, rule stop, rule target, and shares capital. The specific data points were: date of 2026-09-17, 432 items, close price of 45.55, prior 20-day average of 43.15, 50-day simple moving average of 35.784, 200-day simple moving average of 55.52105, 20-day average true range of 2.263305, average true range as a percentage of 4.96883644, 20-day realized volatility of 0.8066348, 20-day average volume of 345649.2, signal of true, rule stop of 41.02339, rule target of 59.12983, and shares capital of 2. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=PSIX&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline 'BWLP R91806 backtests 2/2'. Methods note3577 used a September 2018 calculation on completed September 2017 bars. The results are based on percent units and simulations that are conditional, with a Kelly diagnostic, which is a measure of risk. The results are as follows: the columns are split, lookback, filter, cost basis points per side, bars, return percent, closed return percent, drawdown percent, win rate percent, number of trades, mean trade percent, median trade percent, open, buy and hold percent, targets, and gaps. The rows show the following data: for forward2026 with a 20-day lookback and sma50 filter, the cost was 16 basis points per side, with 178 bars, a return of 119.94 percent, a closed return of 110.18 percent, a drawdown of 11.13 percent, a win rate of 83.33 percent, 6 trades, a mean trade return of 13.60 percent, a median trade return of 15.05 percent, an open of 1, a buy and hold return of 126.32 percent, 5 targets, and 0 gaps. Other rows show similar data for different lookback periods and filters, including sma50 with 40-day lookback and 6 basis points per side, sma50 with 40-day lookback and 16 basis points per side, none with 20-day lookback and 6 basis points per side, sma200 with 20-day lookback and 6 basis points per side, and spy200 with 20-day lookback and 6 basis points per side, with returns ranging from 70.52 to 133.39 percent. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=BWLP&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline is not available, but a data line was found. The data line is a methods note, number 3577, from September 2018, which is a calculation based on completed September 2017 bars. The calculations are in percent units and the simulations are conditional, with a Kelly diagnostic. The data includes the following information: a table with columns for split, lookback, filter, cost basis points per side, bars, return percent, closed return percent, drawdown percent, win rate percent, the number of trades, mean trade percent, median trade percent, open, buy and hold percent, targets, and gaps. The rows of the table include the following data: holdout with 10, 20, and 40 lookback periods, and different filters, including sma50, none, and sma200, with various costs and results, and forward2026 with 10 and 20 lookback periods and sma50 filter, with different costs and results. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=BWLP&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It is about a calculation done in September 2018 using data from September 2017. The calculation is measured in percent units and the results are based on certain conditions. A Kelly diagnostic was also used, which is a tool to measure the performance of an investment strategy. The results are shown in a table with the following information: the type of data set, the regime, whether the results are above a certain point, the number of times this happened, the average percentage change, and the percentage of times it was a win. The table shows the following results: for the holdout set and own200 regime, when the results were above a certain point, this happened 2 times, with an average percentage change of 6.3241865 and a win percentage of 50. When the results were not above a certain point, this happened 5 times, with an average percentage change of -6.59768957 and a win percentage of 0. For the holdout set and spy200 regime, when the results were above a certain point, this happened 7 times, with an average percentage change of -2.90572498 and a win percentage of 14.28571429. For the forward2026 set and own200 regime, when the results were above a certain point, this happened 6 times, with an average percentage change of 13.82792422 and a win percentage of 83.33333333. For the forward2026 set and spy200 regime, when the results were above a certain point, this happened 5 times, with an average percentage change of 11.60869402 and a win percentage of 80. When the results were not above a certain point, this happened 1 time, with an average percentage change of 24.92407519 and a win percentage of 100. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=BWLP&timeframe=1Day&feed=sip&adjustment=all

A news scan found the trade statistics for BWLP R91806. The statistics were calculated on September 18, using data from completed bars in September 17. The calculations are in percent units and include simulations that are conditional, with a Kelly diagnostic, which is a measure of investment performance. The statistics are as follows: the columns are split, number of trades, mean percent, mean confidence interval 95 percent, win percent, average win percent, average loss percent, half Kelly stock fraction, half Kelly dollars, minimum trade percent, and maximum trade percent. The rows show two sets of data, one for holdout and one for forward2026. For holdout, there were 7 trades, with a mean percent of -2.90572498, a mean confidence interval 95 percent of -7.08372339 to 4.35912412, a win percent of 14.28571429, an average win percent of 18.18405554, an average loss percent of 6.4206884, a half Kelly stock fraction of 0, half Kelly dollars of 0, a minimum trade percent of -8.71837268, and a maximum trade percent of 18.18405554. For forward2026, there were 6 trades, with a mean percent of 13.82792422, a mean confidence interval 95 percent of 5.55962868 to 20.34814955, a win percent of 83.33333333, an average win percent of 17.66339012, an average loss percent of 5.34940528, a half Kelly stock fraction of 0.5, half Kelly dollars of 101.99, a minimum trade percent of -5.34940528, and a maximum trade percent of 24.92407519. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=BWLP&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was made. It was about a calculation done in September 2018 using data from September 2017. The calculation used something called percent units, which are a way to measure change. It also used simulations, which are like practice runs, and a Kelly diagnostic, which is a tool to help make decisions. The results are shown in a table with the following information: the name of the group, the number of items, the smallest gap as a percentage, the gap at the 1 percent level, the gap at the 0.1 percent level, the number of times the value was below 10, 20, and 30 percent, and the smallest and largest closing values as a percentage. The table has two rows of data: one for a group called holdout with 420 items, and one for a group called forward2026 with 178 items. The holdout group had a smallest gap of -13.29887218 percent, a gap at the 1 percent level of -5.34961551 percent, and a gap at the 0.1 percent level of -11.35093085 percent. It had one time below 10 percent, and the smallest and largest closing values were -15.24906015 percent and 18.52713178 percent. The forward2026 group had a smallest gap of -10.47865459 percent, a gap at the 1 percent level of -4.6025945 percent, and a gap at the 0.1 percent level of -9.51349459 percent. It had one time below 10 percent, and the smallest and largest closing values were -10.47865459 percent and 5.49295775 percent. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=BWLP&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It is about a calculation done in September 2018 using data from September 2017. The calculation uses percentages and is based on certain conditions, with a diagnostic tool called Kelly. A news scan found the following data: a table with many columns, including date, number of items, closing price, and signal, and one row of data for September 17, 2026, with a closing price of 26.14, and other values such as 25.84 for prior20, 22.0448 for sma50, and 3 for shares_cap. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=BWLP&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written in September 2018, based on calculations from September 2017 data. The calculations are shown in percent units and the simulations are conditional, using a Kelly diagnostic, which is a tool to measure risk. The results are shown in a table with the following columns: the probability of replacing a tail, the weight of equity, the number of paths, the number of trades, the average terminal percentage, the fifth percentile terminal percentage, the ninety-fifth percentile drawdown percentage, and the probability of a ten percent loss. The table has the following rows: [0, 0.11999953, 20000, 20, 3.57058835, -8.64104101, 11.41405973, 3.155], [0, 0.02999988, 20000, 20, 0.88197683, -2.20071571, 2.9681861, 0], [0.01, 0.11999953, 20000, 20, 2.75025592, -9.62294399, 12.26271041, 4.36], [0.01, 0.02999988, 20000, 20, 0.68102337, -2.45808694, 3.19355647, 0], [0.05, 0.11999953, 20000, 20, -0.24269729, -13.14664014, 15.38272677, 11.615], [0.05, 0.02999988, 20000, 20, -0.06038226, -3.40933736, 4.04640533, 0]. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline 'Methods note3577'. This is a note about methods. A calculation was done on September 18, using data from September 17. The calculation used percent units and was based on certain conditions. It also used something called a Kelly diagnostic, which is a way to measure risk. The results of the calculation are shown in a table with many columns, including period, block, levels, paths, horizon, stop, target, and others. The table has four rows of data, each representing a different set of conditions. The conditions are labeled 'pre2024' and 'last252', which refer to time periods. The data in the table includes numbers like 54.39751, 70.04747, and 2.02, which represent things like stop and target prices, and percentages like 66.77 and 31.21, which represent the results of the calculation. The table also includes lists of dictionaries, which contain more detailed data, including dollars and probabilities, such as 25.4975 and 0.29096479. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline 'LPG R91806 backtests 3/3'. Methods note3577 is a set of rules for the backtest, which is a simulation of trades. The backtest used data from September 2017, calculated in September 2018. The results are shown as percentages. A Kelly diagnostic is a tool to measure the performance of the trades. The backtest results are as follows: the columns are split, lookback, filter, cost in basis points per side, number of bars, return percentage, closed return percentage, drawdown percentage, win rate percentage, number of trades, mean trade percentage, median trade percentage, open, buy and hold percentage, targets, and gaps. The rows show three different scenarios, all with the same results: forward2026 with 20 lookback, no filter, 6 basis points cost per side, 178 bars, 90.90% return, 76.56% closed return, 11.99% drawdown, 57.14% win rate, 7 trades, 9.38% mean trade, 15.07% median trade, 1 open, 153.96% buy and hold, 4 targets, and 0 gaps, with the filter being none, sma200, and spy200 respectively. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline 'Methods note3577'. This refers to a note about methods used in a calculation. The calculation was done in September 2018 and used completed data from September 2017. The results are given in percent units and the simulations are conditional, which means they depend on certain conditions being met. A Kelly diagnostic was also used, which is a tool to help make decisions. The results of the simulations are given in a table with the following columns: split, lookback, filter, cost_bps_side, bars, return_pct, closed_return_pct, drawdown_pct, win_rate_pct, n, mean_trade_pct, median_trade_pct, open, buyhold_pct, targets, gaps. The table has 11 rows of data, each representing a different set of conditions. For example, the first row has a split of 'holdout', a lookback of 20, a filter of'sma50', and a cost_bps_side of 16. The return_pct for this row is -27.1315263, the closed_return_pct is also -27.1315263, and the drawdown_pct is 41.02970449. The data is for the LPG R91806 and covers the period from September 2017 to 2026. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline is not available, but a data line shows backtest results for LPG R91806. Methods note3577 states that the calculation was done in September 2018 on completed September 2017 bars, using percent units and conditional simulations with Kelly diagnostic. The results are as follows: a table with columns for split, lookback, filter, cost basis points per side, bars, return percent, closed return percent, drawdown percent, win rate percent, number of trades, mean trade percent, median trade percent, open, buy and hold percent, targets, and gaps. The rows show the following data: train and holdout periods with different lookback periods, filters such as sma50, sma200, and spy200, and various costs and returns. For example, the train period with a 10-day lookback, sma50 filter, and 6 basis points cost per side had a return of 231.09 percent and a drawdown of 69.23 percent. The holdout period with a 10-day lookback, sma50 filter, and 6 basis points cost per side had a return of -15.40 percent and a drawdown of 43.81 percent. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It used a September 2018 calculation based on completed September 2017 data. The calculation used percent units and was based on conditional simulations, which included a Kelly diagnostic, a measure of risk. The results were presented in a table with the following information: the type of data set, the regime, whether the data was above a certain point, the number of data points, the average percent change, and the percent of winning trades. The table had the following rows: for the training data set, the own200 regime with data above a certain point had 38 data points, an average percent change of 1.19860734, and a win percentage of 28.94736842, the own200 regime with data below a certain point had 11 data points, an average percent change of 2.3984803, and a win percentage of 36.36363636, the spy200 regime with data above a certain point had 38 data points, an average percent change of 1.01753344, and a win percentage of 28.94736842, and the spy200 regime with data below a certain point had 11 data points, an average percent change of 3.02400833, and a win percentage of 36.36363636. For the holdout data set, the own200 regime with data above a certain point had 6 data points, an average percent change of -3.75677909, and a win percentage of 16.66666667, the own200 regime with data below a certain point had 4 data points, an average percent change of -0.20236628, and a win percentage of 25, the spy200 regime with data above a certain point had 8 data points, an average percent change of -1.0339292, and a win percentage of 25, and the spy200 regime with data below a certain point had 2 data points, an average percent change of -7.53935305, and a win percentage of 0. For the forward2026 data set, the own200 regime with data above a certain point had 7 data points, an average percent change of 9.38416228, and a win percentage of 57.14285714, and the spy200 regime with data above a certain point had 7 data points, an average percent change of 9.38416228, and a win percentage of 57.14285714. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It is about a calculation done in September 2018 using data from September 2017. The calculation is shown in a table with many columns, including the mean percentage, which is a measure of average change, and the win percentage, which is the percentage of trades that made money. The table has three sections: train, holdout, and forward2026. The data is as follows: the train section has 49 trades with a mean percentage of 1.46796658, the holdout section has 10 trades with a mean percentage of -2.33501397, and the forward2026 section has 7 trades with a mean percentage of 9.38416228. A Kelly diagnostic, which is a tool used to determine the best size for a trade, was also used in the simulation, which is a test of how a trading strategy would have worked in the past. The half Kelly stock fraction, which is the percentage of the portfolio that should be invested in a stock according to the Kelly criterion, is also shown, with values of 0.3845 for the train section, 0 for the holdout section, and 0.5 for the forward2026 section. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was made. It used a September 2018 calculation on completed September 2017 bars. The units are in percent and are explicitly named. The simulations are conditional and include a Kelly diagnostic. A data set was found with the following columns: split, n, min_gap_pct, p01_gap_pct, p001_gap_pct, below10, below20, below30, min_close_pct, and max_close_pct. The rows of data are: train with 2011, -22.27513228, -3.73434732, -8.92869342, 2, 1, 0, -24.77434679, and 20.80536913; holdout with 502, -10.12514221, -4.06876486, -10.0324908, 1, 0, 0, -13.8225256, and 12.89308176; and forward2026 with 178, -5.48817465, -3.73549045, -5.17890595, 0, 0, 0, -8.61127956, and 12.75670452. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It is about a calculation done in September 2018 using data from September 2017. The calculation is shown in percent units and simulations are conditional, using a Kelly diagnostic, which is a way to measure risk. A news scan found the following data: a table with columns for date, a number, close price, prior 20-day average, 50-day simple moving average, 200-day simple moving average, 20-day average true range, 20-day average true range percent, 20-day realized volatility, 20-day volume, a signal, a stop rule, a target rule, and shares capital. The table has one row of data for September 17, 2026, with the following values: the number 2692, a close price of 58.31, a prior 20-day average of 57.86, a 50-day simple moving average of 47.5036, a 200-day simple moving average of 36.2537, a 20-day average true range of 1.956245, a 20-day average true range percent of 3.35490482, a 20-day realized volatility of 0.34295177, a 20-day volume of 568688.85, a signal of true, a stop rule of 54.39751, a target rule of 70.04747, and shares capital of 1. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline 'STNG R91806 backtests 3/3'. The backtest results for STNG R91806 are based on a September 2018 calculation using completed September 2017 bars. The results are given in percent units and the simulations are conditional, with a Kelly diagnostic, which is a measure of risk. The results are as follows: the columns are split, lookback, filter, cost in basis points per side, number of bars, return percent, closed return percent, drawdown percent, win rate percent, number of trades, mean trade percent, median trade percent, open, buy and hold percent, targets, and gaps. The rows show three different scenarios for forward2026 with a lookback of 20, and different filters: none, sma200, which is a simple moving average over 200 periods, and spy200. The results for each scenario are: return percent of -10.6772242, closed return percent of -17.59264327, drawdown percent of 25.8586376, win rate percent of 14.28571429, 7 trades, mean trade percent of -2.23814958, median trade percent of -5.93009833, open of 1, buy and hold percent of 76.90293999, targets of 1, and gaps of 0. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=STNG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline 'STNG R91806 backtests 2/3'. Methods note3577 is a calculation method used for the backtest, which was done in September 2018 on completed September 2017 bars. The calculations are in percent units and the simulations are conditional, with a Kelly diagnostic, which is a measure of risk. The results are as follows: a table with columns for split, lookback, filter, cost in basis points per side, number of bars, return percentage, closed return percentage, drawdown percentage, win rate percentage, number of trades, mean trade percentage, median trade percentage, open, buy and hold percentage, targets, and gaps. The rows of the table are: holdout with 20, 40, and other lookback periods, and forward2026 with 10, 20, and 40 lookback periods, each with different filters and costs. For example, one row is for holdout with a lookback of 20, a filter of sma50, a cost of 16 basis points per side, 502 bars, a return of 5.121106 percent, a closed return of 5.121106 percent, a drawdown of 27.08659826 percent, a win rate of 33.33333333 percent, 9 trades, a mean trade of 1.1746132 percent, a median trade of -6.02178231 percent, 0 open, a buy and hold of -14.33716344 percent, 1 target, and 2 gaps. Another row is for forward2026 with a lookback of 10, a filter of sma50, a cost of 6 basis points per side, 178 bars, a return of 8.7173268 percent, a closed return of -2.86961625 percent, a drawdown of 20.74706418 percent, a win rate of 33.33333333 percent, 6 trades, a mean trade of 0.06981829 percent, a median trade of -5.91456631 percent, 1 open, a buy and hold of 76.90293999 percent, 1 target, and 0 gaps. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=STNG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the headline 'STNG R91806 backtests 1/3'. Methods note3577 is a calculation method used for this backtest, which was done in September 2018 on completed bars from September 2017. The calculations are in percent units and the simulations are conditional, using a Kelly diagnostic, which is a tool to measure the performance of a trading strategy. The results are as follows: a table with 12 rows and 15 columns, including split, lookback, filter, cost_bps_side, bars, return_pct, closed_return_pct, drawdown_pct, win_rate_pct, n, mean_trade_pct, median_trade_pct, open, buyhold_pct, targets, and gaps. The table shows data for different combinations of lookback, filter, and cost_bps_side, with results such as return_pct ranging from -58.95473799 to 7.30918808, and win_rate_pct ranging from 25.49019608 to 33.33333333. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=STNG&timeframe=1Day&feed=sip&adjustment=all

A methods note, number 3577, was written. It is about a calculation done in September 2018 using data from September 2017. The calculation is based on percent units and includes simulations that are conditional, with a Kelly diagnostic, which is a tool to measure risk. The results are shown in a table with the following columns: split, regime, above, number of times, mean percent, and win percent. The table has the following rows: train own200 with 20 times above, mean percent 1.69618872, and win percent 35, train own200 with 22 times not above, mean percent -1.6953654, and win percent 22.72727273, train spy200 with 30 times above, mean percent 1.45974976, and win percent 30, train spy200 with 12 times not above, mean percent -3.93056309, and win percent 25, holdout own200 with 7 times above, mean percent -0.17207846, and win percent 28.57142857, holdout own200 with 2 times not above, mean percent 6.79951773, and win percent 50, holdout spy200 with 8 times above, mean percent -1.00465779, and win percent 25, holdout spy200 with 1 time not above, mean percent 20.4317485, and win percent 100, forward2026 own200 with 6 times above, mean percent -1.74664302, and win percent 16.66666667, and forward2026 spy200 with 6 times above, mean percent -1.74664302, and win percent 16.66666667. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=STNG&timeframe=1Day&feed=sip&adjustment=all

A news scan found the trade statistics for STNG R91806. The statistics were calculated on September 18, using data from completed bars in September 17. The calculations are based on percent units and include simulations that are conditional, with a Kelly diagnostic, which is a measure of investment performance. The statistics are presented in a table with the following columns: split, n, mean percent, mean confidence interval 95 percent, win percent, average win percent, average loss percent, half Kelly stock fraction, half Kelly dollars, minimum trade percent, and maximum trade percent. The rows in the table are: train, with 42 data points, a mean percent of -0.08033963, a mean confidence interval 95 percent of -4.59924627 to 4.78847572, a win percent of 28.57142857, an average win percent of 23.93251371, an average loss percent of 9.68548096, a half Kelly stock fraction of 0, half Kelly dollars of 0, a minimum trade percent of -17.03598023, and a maximum trade percent of 37.2643616. Holdout, with 9 data points, a mean percent of 1.37716513, a mean confidence interval 95 percent of -5.99263103 to 9.46450355, a win percent of 33.33333333, an average win percent of 16.62114664, an average loss percent of 6.24482562, a half Kelly stock fraction of 0.5, half Kelly dollars of 101.99, a minimum trade percent of -6.9121708, and a maximum trade percent of 23.24288961. Forward2026, with 6 data points, a mean percent of -1.74664302, a mean confidence interval 95 percent of -7.33325834 to 8.37469849, a win percent of 16.66666667, an average win percent of 23.17679547, an average loss percent of 6.73133072, a half Kelly stock fraction of 0, half Kelly dollars of 0, a minimum trade percent of -8.44435981, and a maximum trade percent of 23.17679547. https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=STNG&timeframe=1Day&feed=sip&adjustment=all