A news scan found the notes from a trading fund manager. The notes were corrected on 1833 after being frozen from 1829 to 1831. The manager used a method called SIP, which is a way to adjust data, and adjusted the data from 2016 as a warm-up. The manager then trained the system from 2017 to 2019, held out from 2020 to 2025, and used 2026 separately. The manager excluded a type of exit called era-crossing exits. The manager used a mode called swing, which is a type of trading strategy. The published price was the close of the second-to-last day, and the calendar price was the open of the last day of the month to the close of the third month. The control was sessions 10 to 13. The swing strategy used a calendar with a prior ADR, which is a type of average price, of 20, a stop of 1.5 times the average true range, which is a measure of price movement, and a target of 1.5 times the average true range. The fees were 1 basis point, which is a unit of measurement for interest rates, plus slippage of 15 basis points per side. The manager used a factor called k, which is a measure of risk, of 1.25. The manager had eight independent cash sleeves, which are parts of a portfolio, with initial equal weights and no rebalancing between ETFs, which are types of investments. The manager used daily close drawdown, which is a measure of loss, and not intraday drawdown. The manager used a custom max error of 1.67e-15, which is a measure of accuracy. The results were measured by columns including symbol, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, mean percentage, quarter Kelly, which is a measure of risk, and buy-hold percentage. The results were as follows: SPY had a return of -6.26%, IWM had a return of -15.92%, EFA had a return of -4.73%, EEM had a return of -9.58%, EWJ had a return of -7.46%, EWU had a return of -15.19%, EWC had a return of -4.97%, and EWA had a return of -4.01%. The data was from the source https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from a trading fund manager. The notes were corrected on 1831 and 1833. The manager used a method called SIP, which is a way to adjust data, and trained the model from 2016 to 2019, held out data from 2020 to 2025, and used 2026 separately. The manager excluded a type of exit called era-crossing exits. The mode used was swing, which is a type of trading strategy, and the published data was the close of the second-to-last day and the close of the third month. The calendar used was the open of the last day and the close of the third month. The control was sessions 10 to 13. The swing strategy used a stop, which is a price level to buy or sell, and a target, which is a price level to sell, with a ratio of 1.5, and a half plus one R, which is a measure of risk. The fees were 1 basis point, which is a unit of measurement for interest rates, plus slippage, which is the difference between the expected price and the actual price, of 15 basis points per side. The manager used a factor called k, which is a measure of volatility, of 0.75. There were eight independent cash sleeves, which are parts of a portfolio, with initial equal weights, and no rebalancing, which is the process of adjusting the portfolio, between ETFs. The daily close and drawdown, which is a measure of loss, were used. The manager used a custom max error of 1.67e-15, which is a measure of the maximum allowed error. The results were as follows: for SPY, the return was -11.82%, the drawdown was -12.43%, and the win percentage was 37.14%; for IWM, the return was -8.50%, the drawdown was -11.89%, and the win percentage was 48.57%; for EFA, the return was -10.06%, the drawdown was -10.84%, and the win percentage was 37.14%; for EEM, the return was -6.49%, the drawdown was -7.28%, and the win percentage was 42.86%; for EWJ, the return was -8.02%, the drawdown was -10.11%, and the win percentage was 51.43%; for EWU, the return was -12.62%, the drawdown was -13.76%, and the win percentage was 31.43%; for EWC, the return was -12.72%, the drawdown was -12.72%, and the win percentage was 28.57%; for EWA, the return was -9.25%, the drawdown was -9.90%, and the win percentage was 40%. The data used was current and survivor ETFs, adjusted prices, and not raw dividend, whole-share, 3 entry cap or overnight 15 minutes validated. There was no promote holdout neighbors. The source of the data was https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from a trading fund manager. The notes were corrected on 1831 and 1833. The manager used a method called SIP, which is a way to adjust data, and trained the system from 2016 to 2019, held out data from 2020 to 2025, and used 2026 separately. The manager excluded certain types of exits, which are when the system sells a stock. The mode used was swing, which is a type of trading strategy. The manager published results based on the close of the stock on the last day of the month and the close of the stock on the third month after that. The manager also used a calendar, which is a way to schedule trades, and controlled the system during sessions 10 to 13. The swing strategy used a stop, which is a price at which the system sells a stock, and a target, which is a price at which the system aims to sell a stock, with a stop of 20 and a target of 1.5 times that. The manager also used a daily stop, which is a price at which the system sells a stock during the day, and a gap open, which is when the stock opens at a different price than it closed at the day before. The fees were 1 basis point, which is a unit of measurement for interest rates, plus slippage, which is the difference between the expected price of a trade and the actual price, of 15 basis points per side. The manager used 8 independent cash sleeves, which are like separate accounts, with initial equal weights, which means each account had the same amount of money, and no rebalancing, which is when the manager adjusts the accounts to keep them equal. The manager also used a daily close drawdown, which is a measure of how much the system has lost, and no intraday drawdown, which is a measure of how much the system has lost during the day. The manager used a custom max error, which is a measure of how accurate the system is, of 1.67e-15. The results were presented in columns, including the symbol of the stock, the return percentage, the drawdown percentage, the number of trades, the win percentage, the average win percentage, the average loss percentage, the mean percentage, the quarter Kelly, which is a measure of how well the system is doing, and the buy and hold percentage, which is how well the system would have done if it had just bought and held the stock. The results were as follows: SPY had a return of -7.054%, IWM had a return of -17.098%, EFA had a return of -10.983%, EEM had a return of -8.399%, EWJ had a return of -6.218%, EWU had a return of -13.992%, EWC had a return of -9.578%, and EWA had a return of -11.100%. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from a trading fund manager. The notes were corrected on 1831 and 1833. The manager used a method called SIP, which is a way to adjust prices, and trained the model from 2016 to 2019, held out from 2020 to 2025, and used 2026 separately. The manager excluded a type of exit called era-crossing exits. The mode used was swing, which is a type of trading strategy, and the manager published the results based on the penultimate close and the third next month close. The calendar used was from the last day open to the third next month close, and the control was based on sessions 10 to 13. The swing strategy used a prior ADR, which is a type of stock price, with a 20 stop and a target of 1.5, and a half plus 1R, which is a type of risk management, and a BE, which is a break-even point, following day, and a daily stop at the first gap open. The fees were 1 basis point plus slippage of 5 basis points per side. The manager used a factor called k, which is a type of multiplier, of 1.25. There were eight independent cash sleeves with initial equal weights and no inter-ETF rebalance, and daily close drawdown, which is a type of loss, and no intraday drawdown. The manager used a custom max error of 1.67e-15. The results were based on columns including symbol, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, mean percentage, quarter Kelly, which is a type of betting strategy, and buy hold percentage. The results were as follows: for SPY, the return was 0.5338265383880714, the drawdown was -9.238948170892646, and the win percentage was 54.285714285714285; for IWM, the return was -9.820185658433322, the drawdown was -15.678668158114274, and the win percentage was 42.857142857142854; for EFA, the return was 2.1801532842328664, the drawdown was -8.882010573866662, and the win percentage was 57.14285714285714; for EEM, the return was -3.028591261731328, the drawdown was -12.3072767269781, and the win percentage was 48.57142857142857; for EWJ, the return was -0.7539478378133291, the drawdown was -9.206101043911586, and the win percentage was 60; for EWU, the return was -9.038114704081169, the drawdown was -14.037066198451987, and the win percentage was 45.714285714285715; for EWC, the return was 1.9155977578675598, the drawdown was -5.1816000508775435, and the win percentage was 54.285714285714285; and for EWA, the return was 2.952398438309345, the drawdown was -6.0291043358090874, and the win percentage was 57.14285714285714. The source of the data was https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from a trading fund manager. The notes were corrected on dates 1829, 1831, and 1833. The manager used a method called SIP, which is a way to adjust data, and adjusted the data from 2016 as a warm-up. The manager then trained the system from 2017 to 2019, held out data from 2020 to 2025, and used 2026 separately. The manager excluded a type of exit called era-crossing exits. The manager used a mode called swing, which is a type of trading strategy, and published results based on the close of the market on the last day of the month and the close of the market on the third month after that. The manager also used a calendar-based system with a stop-loss, which is a way to limit losses, and a target, which is a profit goal. The manager used a type of analysis called vectorbt, which is a way to analyze data, and set a custom maximum error of 1.67e-15. The manager looked at eight ETF cells, which are a type of investment, with equal initial weights and no rebalancing between them. The manager calculated daily drawdown, which is a measure of losses, but not intraday drawdown. The results are as follows: for SPY, the return was -5.427553436033239 percent, the drawdown was -6.512707561540909 percent, and there were 35 trades; for IWM, the return was -1.8656586294187205 percent, the drawdown was -8.847944652172867 percent, and there were 35 trades; for EFA, the return was -3.533855877730818 percent, the drawdown was -7.586895231021495 percent, and there were 35 trades; for EEM, the return was 0.2941768613182516 percent, the drawdown was -5.047760223330588 percent, and there were 35 trades; for EWJ, the return was -1.353924900174075 percent, the drawdown was -6.260858905260658 percent, and there were 35 trades; for EWU, the return was -6.283454207174821 percent, the drawdown was -9.281314262366614 percent, and there were 35 trades; for EWC, the return was -6.392140800553115 percent, the drawdown was -7.761491723490332 percent, and there were 35 trades; for EWA, the return was -2.6663735776952024 percent, the drawdown was -5.8539298250049 percent, and there were 35 trades. The manager used current survivor ETFs and adjusted prices, but not raw dividend data, and whole-share data with a 3-entry cap or overnight 15-minute validation. The manager did not promote holdout neighbors. The data source is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
The automated trading fund manager's notes from 1829 to 1831 were corrected in 1833. The fund used a warm-up period from 2016, trained from 2017 to 2019, and held out from 2020 to 2025, with 2026 being separate. The fund excluded era-crossing exits. The mode was set to swing, which means it followed a specific strategy. The published price was the penultimate close, and the calendar price was the last day's open to the third next month's close. The control sessions were from 10 to 13. The swing strategy used a calendar with a prior ADR, which stands for Average Daily Range, of 20, a stop of 1.5 times that, and a half plus 1 risk management strategy. The fees were 1 basis point plus slippage of 5 basis points per side. There were eight independent cash sleeves with initial equal weights and no inter-ETF rebalance. The daily close and drawdown, which refers to the peak-to-trough decline, were tracked, but not the intraday drawdown. The vectorbt custom max error was set to 1.67e-15. The results included columns for symbol, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, mean percentage, quarter Kelly, which is a measure of risk, and buy-hold percentage. The results for the ETFs were as follows: SPY had a return of -0.31477357221252333%, IWM had a return of -11.087316764583854%, EFA had a return of -4.528075649865482%, EEM had a return of -1.7576012107707761%, EWJ had a return of 0.58227782075706%, EWU had a return of -7.7559871849756545%, EWC had a return of -3.0217715669913603%, and EWA had a return of -4.654149322438772%. The current survivor ETFs were adjusted for prices, but not for raw dividend or whole-share, and had a 3 entry cap or overnight 15-minute validation. There was no promote holdout neighbors. The source of the data was https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from a trading fund manager. The notes were corrected on 1831 and 1833. The manager used a method called SIP, which is a way to adjust data, and trained it from 2016 to 2019, held out from 2020 to 2025, and used 2026 separately. The manager excluded a type of exit called era-crossing exits. The manager used a mode called control, which means they made decisions based on the penultimate close, or the close before the last one, and the third next month close. They also used a calendar, which is a way to organize time, and looked at the last day open and the third next month close. The manager controlled sessions 10 to 13 and used a swing, which is a type of trading strategy, with a prior ADR, or average daily range, of 20, a stop, or a price to sell, of 1.5k, and a target, or a price to buy, of 1.5k. The manager also used a daily stop, which is a price to sell, and a gap open, which is a big change in price. The fees were 1 basis point, or a small unit of measurement, plus slippage, or the difference between the expected price and the actual price, of 15 basis points per side. The manager used a factor called k, which is a way to measure risk, of 1. The manager had eight independent cash sleeves, which are like separate accounts, with initial equal weights, and no inter-ETF rebalance, which means they did not move money between the accounts. The manager looked at daily close drawdown, which is a measure of loss, and not intraday drawdown, which is a measure of loss during the day. The manager used a custom max error of 1.67e-15, which is a very small number. The columns in the data were symbol, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, mean percentage, quarter Kelly, which is a way to measure risk, and buy hold percentage. The data included the following ETFs: SPY, IWM, EFA, EEM, EWJ, EWU, EWC, and EWA, with their respective return percentages, drawdown percentages, and other metrics. The data was current and used survivor ETFs, which are ETFs that are still trading, and adjusted prices, which are prices that have been changed to reflect dividends and other factors. The manager did not promote holdout neighbors, which means they did not use certain data to make decisions. The source of the data was https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from a trading fund manager. The notes were corrected on 1831, 1833, and 1829. The manager used a method called SIP, which is a way to adjust data, and trained it from 2016 to 2019, held out data from 2020 to 2025, and used 2026 separately. The manager excluded certain types of exits, which are when the fund stops investing in something. The manager had different modes of control, including one that used the price of something at the end of the day, and another that used the price at the end of the month. The manager also used something called a swing, which is a type of investment strategy, with a stop, which is a price at which the fund stops investing, and a target, which is a price at which the fund aims to sell. The manager paid fees of 1 basis point, which is a unit of measurement for interest rates, and 5 basis points for slippage, which is when the price of something changes quickly. The manager used 8 independent cells, which are like separate accounts, with equal weights, which means they were all treated the same. The manager did not rebalance, which means adjust the amounts in each cell, between ETFs, which are types of investments. The manager used a daily close, which is the price at the end of the day, and did not use intraday data, which is data from during the day. The manager used a custom max error, which is a way to measure how accurate something is, of 1.67e-15. The manager looked at columns of data, including symbol, which is a code for a type of investment, return percentage, drawdown percentage, which is a measure of how much something has lost value, and other measures. The data included the following investments: SPY, IWM, EFA, EEM, EWJ, EWU, EWC, and EWA, with their respective return percentages, drawdown percentages, and other measures. The data came from a source at https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all, which is a website that provides financial data.
A news scan found the notes from a trading fund manager. The notes were frozen and then corrected. The manager used a method called SIP to adjust the data from 2016. The manager trained the system using data from 2017 to 2019, held out data from 2020 to 2025, and used 2026 separately. The manager excluded certain types of exits, which are when the system sells a stock. The system uses a calendar, which is a way of organizing time, and it looks at the last day of the month and the next three months. The manager also used something called ADR, or average daily range, which is a measure of how much a stock's price moves in a day, and a stop, which is a price at which the system sells a stock to limit losses. The manager also used a target, which is a price at which the system sells a stock to make a profit. The manager paid fees of 1 basis point, which is a unit of measurement for interest rates, and 15 basis points for slippage, which is when the system buys or sells a stock at a different price than expected. The manager used eight separate accounts, called cash sleeves, with equal amounts of money in each. The manager looked at the daily closing prices, not the prices during the day. The manager used a system called vectorbt and set a maximum error of 1.67e-15. The manager looked at several pieces of data, including the symbol of the stock, the return, which is the profit or loss, the drawdown, which is the amount of money lost, and the win percentage, which is the percentage of trades that made a profit. The manager looked at the following stocks: SPY, IWM, EFA, EEM, EWJ, EWU, EWC, and EWA. The data for these stocks included the return, drawdown, number of trades, win percentage, average win, average loss, mean return, quarter Kelly, which is a measure of how much to bet, and buy hold percentage, which is the percentage of the time that the system would have made a profit if it had just bought and held the stock. The data was as follows: SPY had a return of -10.93%, IWM had a return of -16.13%, EFA had a return of -12.83%, EEM had a return of -13.73%, EWJ had a return of -10.28%, EWU had a return of -20.46%, EWC had a return of -13.97%, and EWA had a return of -16.59%. The manager used adjusted prices, not raw dividend prices, and whole shares, not fractions of shares. The manager did not promote holdout neighbors, which are stocks that are similar to the ones being traded. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from an automated trading fund manager. The notes were corrected on 1831 and 1833. The manager used a method called SIP, which is a way to adjust data, and trained the system from 2016 to 2019, held out data from 2020 to 2025, and used 2026 separately. The manager excluded a type of exit called era-crossing exits. The system used a calendar mode, which means it looked at data from the last day of the month to the third month after that. The manager also used something called ADR, which stands for Average Daily Range, a measure of how much prices move. The fees were 1 basis point, which is a unit of measurement for interest rates, plus 5 basis points for slippage, which is the difference between expected and actual prices. There were eight independent parts, called cash sleeves, with equal weights and no rebalancing between them. The manager used a custom error limit of 1.67e-15. The results included columns for symbol, return percentage, drawdown percentage, and other metrics. The results for the ETFs were as follows: SPY had a return of -4.47%, IWM had a return of -10.05%, EFA had a return of -6.51%, EEM had a return of -7.47%, EWJ had a return of -3.77%, EWU had a return of -14.70%, EWC had a return of -7.74%, and EWA had a return of -10.54%. The data came from a source called runway.adityaperswal.workers.dev, which provided stock bar data with all adjustments.
A news scan found the headline 'QTOM91006 train published 16 1 eight fixed ETF cells'. Frozen notes from 1829 to 1831 were corrected in 1833. The system was trained from 2016 to 2019, held out from 2020 to 2025, and a separate period was used for 2026. The system excludes era-crossing exits. The mode is published, which means it uses the penultimate close to the third next month close. The calendar uses the last day open to the third next month close. The control uses sessions 10 to 13. The swing uses a calendar with a prior ADR 20 stop, a target of 1.5k, half plus 1R, and a buy entry following the day, with a daily stop at the first gap open. Fees are 1 basis point plus slippage of 15 basis points per side. A basis point is one hundredth of a percent. Slippage refers to the difference between expected and actual trade prices. There are eight independent cash sleeves with initial equal weights and no inter-ETF rebalance. Daily close drawdown and no intraday drawdown are used. Vectorbt is a backtesting library, and custom max error is 1.67e-15. The columns show the symbol, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, mean percentage, quarter Kelly, and buy hold percentage. The data includes the following ETFs: SPY, IWM, EFA, EEM, EWJ, EWU, EWC, and EWA, with their respective return percentages, drawdown percentages, and other metrics. The current survivor ETFs use adjusted prices, not raw dividend, whole-share, and 3 entry cap or overnight 15 minute validated. There is no promote holdout neighbors. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the notes from a trading fund manager. The notes were frozen and then corrected. The manager used a method called SIP to adjust some numbers from 2016. They used the years 2017 to 2019 to train, 2020 to 2025 to hold out, and 2026 separately. They excluded some exits that happened when a stock's price crossed a certain point. The manager had a published mode, which means they used the closing price of the second-to-last day and the closing price of the third month. They also used a calendar that went from the last day of the month to the third month. The manager had control over sessions 10 to 13 and used a swing method with a stop and target. The fees were 1 basis point plus 5 basis points for slippage per side. The manager used 8 independent cash sleeves with equal weights and no rebalancing between ETFs. They used daily close drawdown and not intraday drawdown. A tool called Vectorbt was used with a custom max error. The columns in the data included symbol, return percentage, drawdown percentage, and other numbers. The data included the following ETFs: SPY, IWM, EFA, EEM, EWJ, EWU, EWC, and EWA. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A review of the AVAV company's records shows that they are spending more money and expect to make more profit later on. EBITDA, which is a measure of a company's profit, minus estimated capital expenditures, which is money spent on things like equipment and property, does not equal free cash flow, which is the money left over after paying for these things. The company still needs to carry out and get paid for its funded contracts. As a result, the decision to not use the EAR paper study remains, because having better access to documents does not give an independent advantage in determining the company's stock price. One argument against this decision is that expanding the company's capacity in a profitable way can lead to more cash being generated in the future, but it does not guarantee that the company will make money in the short term. This information comes from the AVAV investor website. The gap between the current stock price and the target price, known as the full-call gap, still exists.
The final decision for QPAIR91004 is to not allocate to cash-only ETF pairs. The goal is to achieve repeatable positive cash-only returns, with a binding constraint of net condition alpha edge under actual exits. Two author papers motivate relative value tests, but their published long-short stock selection differs from this 12 fixed ETF adaptation. Gatev's top 20 long alpha of 1.27 and 101-120 long t2 of 2.85 caution against both blanket adoption and rejection. A frozen 60/2 holdout of 693 trades resulted in a long return of -4.5294% and a drawdown of 20.2127%, with a partner return of -4.59854%. The paired mean return was 0.007491% with a confidence interval of -0.024664% to 0.039776% in 3-month blocks, with a trade correlation of 0.994124 and a partner alpha of 0.127. The actual horizon proxy had a swing return of -7.48274%, a drawdown of 8.06277%, and a mean return of -0.133650%. All 12 swing holdout cells were negative, and three low-cost long neighbor cells were positive but all six stressed long cells were negative. There was no holdout selection. A hedged diagnostic lost 8.57% in the base holdout and is not available in the venue. All 12 current absolute values were less than 2, and even a valid signal would need whole-share, 3 new positions, raw dividend, and 15-minute overnight exit validation. The conclusion is to not propose, exit, adjust, or fund, with an actual size of 0, and to keep cash. The validity of this decision is conditional on SIP provider adjustments, current ETF survivors, cost assumptions, and reused historical era, and does not prove that all statistical arbitrage fails. The strongest counterargument is a 2026 long return of +3.51%, which is mostly partner +3.41%, but this cannot rescue the failed holdout. Evidence to change this decision would require a distinct prospective cost-stressed relative edge plus validated venue path, not another fit to 2020-25. Numeric and code outcomes are archived, with 114 unique cells and 1105 base events. The review is scheduled for 17206 UTC, with 167/168 collectors scheduled, and 15/85 and 42/127/161/171 preserved. Sources include papers from Yale and Berkeley, as well as data from Aditya Perswal.
A news scan found the headline 'QPAIR91004 21-session historical path simulation cannot fund the deadline'. This refers to a simulation of 21 trading sessions using historical data from 2020 to 2025, with 20,000 overlapping portfolio return windows, and a seed of 91004. The simulation preserves the dependence between different pairs of stocks within each window. These are Monte Carlo samples, which means they are random samples of limited realized history, not 20,000 independent market episodes. The simulation used 21 trading sessions, which is longer than the 21 remaining calendar days. The hypothetical base sleeve had a terminal value with a 5th percentile of -1.56858 USD, a 50th percentile of -0.12978 USD, and a 95th percentile of 1.07686 USD, with a loss probability of 58.38%. The stress test had a 5th percentile of -1.92770 USD, a 50th percentile of -0.38730 USD, and a 95th percentile of 0.77307 USD, with a loss probability of 70.49%, and a 5th percentile path drawdown of -1.22515%. None of the sampled paths closed the 349.01 USD gap, but this does not prove it is impossible. The simulation described a hypothetical full sleeve, which was rejected, and fractional diversification, which is not recommended. The required gap was approximately 186.42%, while the base full test annual rate was -1.29128%. The conclusion is that the deadline cannot justify increasing the allocation to a strategy with negative expectancy. The source of this information is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
The QPAIR91004 trading system reported an actual loss. The system's performance metrics include a holdout return of 47.33045%, an average win of 1.162277%, and an average loss of 1.298209%. The payoff ratio is 0.8953, which means the system wins less than it loses, and the required win probability is approximately 52.76%. The quarter Kelly criterion is 0, indicating a conservative approach. The nominal target of 1.5 times the average daily range does not result in an average win of 1.5R because half of the positions are sold at 1R, other exits occur first, and costs reduce the proceeds. The system's exit counts are as follows: target 124, gap target 55, parent open 113, gap stop 71, stop 284, and time close 46, with 259 partial events. There were 298 net losses exceeding 1R, including routine fees, but not 298 gap failures. The worst loss occurred on November 8, 2024, with GLD opening at 249.07 and a prior average daily range of 1.899675, resulting in a loss of -2.662344% or -3.49065R net by November 11. The opening gap is not guaranteed at the stop. The daily bar stop is validated on the next day, but not on a 15-minute or overnight basis. The system's current cash balance is 187.22, and the account balance is 850.99. The nominal account risk is 1% or 8.5099, but the venue risk is 25% or 212.7475, which is bound by the fund cap of 187.22. There are no current holdings or pending trades, and the proposed size is 0. The data source is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all, with a query of trades fund quant.
A news scan found the report that QPAIR91004 correlation is not a convergence clock and there are no current base signals. The report states that all current September 9 close absolute values are less than 2. The maximum ratios are 1.833794 for XLE to VDE and 1.595053 for XLF to VFH, with zero eligible base entries. Same-exposure daily return correlations are high, but diagnostics for the full sample AR drift half-life vary, with 14.21 sessions for SPY and IVV, 193.11 for IWM and IJR, and 877.83 for EFA and VEA. These in-sample AR approximations are not proof of cointegration or forward forecasts and are never used to filter. The current 60 log ratio standard deviations are 0.531146% for SPY to IVV and 0.0180420% for GLD to IAU, meaning a 2 standard deviation means only about 0.1062% or 0.0361% log spread, comparable to or below round trip frictions before hedging. The conclusion is that z-standardization does not guarantee an absolute dollar edge, and correlation does not bound time to convergence. The current indicator combined with a negative costed swing edge results in an allocation of 0. A counterexample is that a sufficiently large idiosyncratic flow could matter, requiring a new independent test. The source is a data feed from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the headline 'QPAIR91004 2026 swing frozen parameter sweep, all12cells'. This is a report from an automated trading fund manager. The manager used a preregistered lookback of 60 or 120 days, which means they looked at the market data from the past 60 or 120 days to make decisions. They also used an xentry of 1.5, 2, or 2.5, which refers to the price at which they entered a trade. The xcost was 6 or 16 bps, which is a measure of the cost of trading, with bps meaning basis points, or a unit of measurement for interest rates and trading costs. The exit strategy was to sell after 0.5 or 10 sessions, which are periods of trading. The swing parent earlier open or 5 session ADR, which stands for Average Daily Range, was used to determine the best time to enter a trade. The ADR is a measure of the average price range of a security over a certain period. The manager used a half plus 1R, which is a risk management strategy, and a BE, or breakeven, following day strategy. The results were measured using a base 60 or 2 decision cell, which means they used a specific set of criteria to make decisions. The portfolios were all cash-only and were reconciled using a custom method with a very small error rate of 4.55e-13. The daily close DD, which refers to the maximum drawdown, or loss, of the portfolio, was also measured. The results were based on 12 independent sleeves, which are separate parts of the portfolio, and current ETF survivors, which are exchange-traded funds that have survived in the market. The results did not include actual 3 new positions, whole-share, or 15-minute venue validation. The data was obtained from a source at https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all. The results are presented in a table with columns for lookback, entryz, bpside, return percentage, DD percentage, N, win percentage, average win percentage, average loss percentage, and mean trade percentage. The table shows the results for different combinations of lookback, xentry, and xcost, with return percentages ranging from -0.54732687668817 to -2.69976468750015, and DD percentages ranging from -0.9448239334113762 to -3.1848498740007836.
A news scan found the headline 'QPAIR91004 2026 partner frozen parameter sweep, all12cells'. The source is a data line from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all. It appears to be a list of trading results with various parameters. The parameters include lookback, which refers to the amount of time used to calculate trading signals, entry, which is the price at which to enter a trade, and bpside, which is a type of trading fee measured in basis points. The results show return percentages, drawdown percentages, and other metrics for different combinations of these parameters. The list includes 12 sets of results with the following values: [[60,2,6,3.4131564952848636,-2.5210388928156524,85,55.294117647058826,2.7062532806392277,2.2792484256888024,0.4774407531043438],[60,2,16,1.9458284757132294,-2.57846801218814,85,52.94117647058824,2.6175583216331755,2.3567943518031274,0.2766864753102092],[60,1.5,6,6.018575168585616,-3.5201054452597247,129,55.03875968992248,2.6915395872429735,2.0073479865564328,0.5788614532866513],[60,1.5,16,3.7618661801841036,-3.712953955723697,129,52.71317829457365,2.6001286105058243,2.099328857306453,0.37790453657908846],[60,2.5,6,0.7120918786366781,-1.8582079570809262,43,55.81395348837209,1.8825944267432826,1.9242956125660584,0.20048022332752732],[60,2.5,16,-0.011390753006634835,-1.9562562535828332,43,51.162790697674424,1.8426251865026122,1.929797315073492,0.0002793136398636214],[120,1.5,6,2.9026855756213443,-4.567855756216687,124,49.193548387096776,2.629597506595963,1.947157319159152,0.30431078060747724],[120,1.5,16,0.8077353288156619,-4.732183913137355,124,45.16129032258064,2.64901687549503,1.9920741956895571,0.10390241710348201],[120,2,6,2.8827204039914234,-2.5134078512216496,67,46.26865671641791,3.4000299635638083,1.90512634439062,0.549498216006205],[120,2,16,1.744104386984624,-2.635554803993767,67,44.776119402985074,3.303395475428498,2.0471801746986076,0.3485999671493503],[120,2.5,6,0.53024381436102,-2.206907447828388,36,61.111111111111114,2.4130203278479314,3.3257235096204005,0.18128661327691348],[120,2.5,16,-0.06733158788386762,-2.2493833084077375,36,55.55555555555556,2.4432307376448184,3.09650930395529,-0.01887594751078556]].
A news scan found the headline 'QPAIR91004 2026 long frozen parameter sweep, all12cells'. The details are about a trading strategy. The strategy has a preregistered lookback of 60 or 120, which means the system looks back at 60 or 120 previous sessions to make decisions. It also has an xentry of 1.5, 2, or 2.5, which refers to the entry point, and a bpside of 6 or 16, which refers to the cost in basis points, a measure of the cost of a trade. The exit strategy is based on.5 or 10 sessions, and a swing parent earlier open or 5 session ADR, which is a measure of the average daily range of a stock. The system does not select the best cell, instead, it uses a base of 60 and 2 as the decision cell. The portfolios are all cash-only and use a vectorbt custom reconcile of 4.55e-13. The daily close is used to calculate the drawdown, which is a measure of the decrease in value of a portfolio. There are 12 independent sleeves, which are groups of stocks, and the current ETF survivors are used, but not actual new positions. The system also uses whole-share and 15-minute venue validation. The results are shown in a table with columns for lookback, entryz, bpside, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, and mean trade percentage. The table shows the results for different combinations of lookback, entryz, and bpside. The data comes from the source https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the headline 'QPAIR91004 holdout swing frozen parameter sweep, all12cells'. The source is a data line from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all. It appears to be a set of trading parameters and results. The parameters include lookback periods of 60 or 120, entry points of 1.5, 2, or 2.5, and costs of 6 or 16 basis points. The exit strategy is based on 0.5 or 10 sessions, and the swing parent is determined by the earlier open or 5-session average daily range. The results are presented in a table with columns for lookback, entry, cost, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, and mean trade percentage. The table contains 12 rows of data, each representing a different combination of parameters. For example, the first row shows a lookback of 60, entry of 2, cost of 6, return of -7.482735811444297 percent, drawdown of -8.062771031087145 percent, 693 trades, win percentage of 47.33044733044733 percent, average win of 1.1622766582272532 percent, average loss of 1.298209026864466 percent, and mean trade of -0.13365014560893357 percent.
A news scan found the headline 'QPAIR91004 holdout partner frozen parameter sweep, all12cells'. This is a report from an automated trading fund manager. The manager tested different trading strategies, also known as a parameter sweep, using historical data from the past 60 and 120 days, which is called the lookback period. The manager used different entry points, or xentry, of 1.5, 2, and 2.5, and different costs, or bpside, of 6 and 16 basis points, which is a measure of the cost of a trade. The manager also tested different exit strategies, including exiting after 0.5 or 10 sessions, or using a swing parent earlier open or 5 session average daily range, which is a measure of the average daily price movement. The results are shown in a table with columns for lookback period, entry point, cost, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, and mean trade percentage. The table shows the results for 12 different combinations of these parameters. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A news scan found the headline 'QPAIR91004 holdout long frozen parameter sweep, all12cells'. This is a report from an automated trading fund manager. The report includes a table with results from different trading strategies. The strategies are defined by several parameters: lookback, which is the amount of time used to calculate the strategy, entryz, which is the price at which to enter a trade, and bpside, which is a type of trading fee, measured in basis points, or 0.01% increments. The report also includes the return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, and mean trade percentage for each strategy. The table shows the results for 12 different combinations of these parameters. The data was sourced from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all. The results are as follows: lookback of 60 or 120 days, entryz of 1.5, 2, or 2.5, and bpside of 6 or 16. The return percentages range from -14.86% to 9.73%, and the drawdown percentages range from -14.84% to -24.06%. The number of trades ranges from 281 to 1250. The win percentages range from 48.24% to 54.56%. The average win percentages range from 2.04% to 2.78%, and the average loss percentages range from 2.12% to 3.42%. The mean trade percentages range from -0.26% to 0.13%.
A news scan found the headline 'QPAIR91004 train swing frozen parameter sweep, all12cells'. The source is a data line from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all. It appears to be a set of trading parameters and results. The parameters include lookback periods of 60 or 120, entry points of 1.5, 2, or 2.5, and costs of 6 or 16 basis points, which is a measure of the cost of a trade as a fraction of the trade value. The results include return percentages, drawdown percentages, and win percentages for different combinations of these parameters. The data is presented in a table with columns for lookback, entry, cost, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, and mean trade percentage. The table contains 12 rows of data, each representing a different combination of parameters. For example, one row shows a lookback of 60, an entry of 2, a cost of 6 basis points, a return of -3.9049%, a drawdown of -4.7856%, 327 trades, a win percentage of 47.0948%, an average win of 0.7343%, an average loss of 0.9407%, and a mean trade percentage of -0.1518%.
A news scan found the headline 'QPAIR91004 train partner frozen parameter sweep, all12cells'. This refers to a set of experiments for an automated trading system. The system was tested with different parameters, including lookback periods of 60 or 120, entry points of 1.5, 2, or 2.5, and costs of 6 or 16 basis points. A basis point is a unit of measurement for interest rates and other financial percentages, equal to one hundredth of a percent. The system would exit after 0.5 or 10 sessions. A session refers to a period of trading activity. The system also considered the average daily range, or ADR, which is a measure of the average daily price movement of a security. The results of the experiments are shown in a table with columns for lookback period, entry point, cost, return percentage, drawdown percentage, number of trades, win percentage, average win percentage, average loss percentage, and mean trade percentage. Drawdown refers to the peak-to-trough decline in the value of a portfolio. The table shows the results of 12 different experiments, including the return percentage, which ranged from -7.359 to 6.066, and the drawdown percentage, which ranged from -4.768 to -13.915. The data came from a source at https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all, which is a URL for a data feed.