This is a frozen specification note. The provider made an adjustment to the Systematic Investment Plan, which started on September 8, 2016, and will end on September 8, 2026. The plan is present for every New York Stock Exchange session for each Exchange-Traded Fund, but it does not include data from 2010 to 2015. The holdout test only includes entries and exits within a certain partition. From 2019 to 2025, there were 83 complete calendar windows and 332 correlated ETF trades, excluding trades that span boundaries. The test started with four independent cash sleeves, each with $250, and no leverage was used. There was no periodic rebalancing between sleeves, and idle cash was set to 0. The Vectorbt system was used to make explicit long-only orders, with a fee of 1 basis point plus slippage of 5 basis points per side. The raw cash return was reconciled with the Vectorbt trade Profit and Loss accounting, taking into account the entry fee denominator. The rule managed the trades as follows: the last session open, a lagged 20-session mean of high-low with a stop at 1 Average Daily Range and a target at 1.5 Average Daily Range, or the third session close. The daily Open-High-Low-Close stop was managed to avoid ambiguity, with adverse gap fills opening and target gap capped at the target. Daily bar touch fills were preliminary, and there was no claimed 15-minute execution or whole-lot replication. A bootstrap of 10,000 complete calendar window means was run across four ETFs, not 332 independent trades. The confidence interval and per-symbol statistics were saved, matching the title. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The sources for this information are https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
This is a frozen specification note. The provider made an adjustment to the Systematic Investment Plan, which includes all NYSE sessions from September 8, 2016, to 2026, for each Exchange-Traded Fund, but does not include data from 2010 to 2015. The holdout test only includes entries and exits within a specific partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, excluding trades that span boundaries. The test started with four independent cash sleeves, each with $250, and no leverage or periodic rebalancing. The Vectorbt system was used to generate explicit long-only orders, with a fee of 1 basis point plus 15 basis points for slippage per side. The rule for opening a position is from the last session's open to the next month's third close. The system manages daily high, low, open, and close prices, with stops and targets set to avoid ambiguity and adverse gap fills. A bootstrap analysis of 10,000 complete calendar window means was conducted across four ETFs. The results include confidence intervals and per-symbol statistics, which are saved with the observation title. The verdict rejects live adoption if uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The sources for this information are https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
This is a frozen specification note1344. The provider made a SIP adjustment from September 8, 2016, to September 8, 2026, which includes every NYSE session for each ETF, but does not include data from 2010 to 2015. The holdout test only includes entries and exits within a certain partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, excluding trades that span boundaries. The test started with four independent cash sleeves, each with $250 in cash, and no leverage was used. The Vectorbt system was used to make explicit long-only trades, with a fee of 1 basis point plus 5 basis points for slippage per side. The rule for opening a trade is to buy at the last session's open and sell at the next month's third close. The system managed daily high, low, open, and close prices, with a stop-loss order to limit losses. A bootstrap analysis was done with 10,000 complete calendar window means across four ETFs. The results are saved with the title. A verdict to reject live adoption was made when uncertainty, cost, and execution gates failed. A news scan found the source https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
This is a frozen specification note. The provider made a SIP adjustment from September 8, 2016, to 2026, including every NYSE session for each ETF, but did not supply data from 2010 to 2015. The holdout test only includes entries and exits within a partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, excluding boundary-spanning trades. The test started with four independent cash sleeves, each with $250, and no leverage or periodic rebalance. The Vectorbt system was used with explicit long-only orders, a fee of 1 basis point, and slippage of 15 basis points per side. The rule for the parent is to buy at the close of the second-to-last session and sell at the close of the third session of the next month. The system managed daily high, low, open, and close prices, with stops and targets set to avoid ambiguity. A study from Purdue University and stock bar data from Aditya Perswal were used as sources.
This is a frozen specification note1344. The provider made a SIP adjustment from September 8, 2016, to 2026, which includes every 2685 NYSE session for each ETF, but does not include data from 2010 to 2015. A holdout test was conducted, which only included entries and exits within a partition. The holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, excluding trades that spanned boundaries. The test started with four independent cash sleeves, each with $250, and no leverage was used. There was no periodic rebalance between sleeves, and idle cash was set to 0. The Vectorbt system was used with explicit long-only orders, a fee of 1 basis point, and slippage of 5 basis points per side. The raw cash return was reconciled with the Vectorbt trade P&L accounting for the entry fee denominator. The rule parent was based on the penultimate session close to the next month's third close. The system managed daily OHLC stops, with ambiguity resolved by stop-first, adverse gap fills open, and target gap capped target. Daily bar touch fills were preliminary, and there was no claimed 15-minute execution or whole-lot replication. A bootstrap of 10,000 complete calendar window means was conducted across four ETFs, not 332 independent trades. Confidence intervals and per-symbol statistics were saved, matching the title of the observation. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The sources for this information are https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
A frozen specification note1344 was made. The provider made a SIP adjustment from September 8, 2016, to 2026, for every 2685 NYSE session, for each ETF, but no data from 2010 to 2015 was supplied. The training and testing only included entries and exits within a certain partition. The holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, and trades that spanned boundaries were excluded. There were four independent cash sleeves, each initially worth 250 USD, with no leverage and no periodic rebalancing between sleeves, and idle cash was set to 0. The vectorbt system was used with explicit long-only orders, a fee of 1 basis point, and slippage of 15 basis points per side. The raw cash return was reconciled with the VBT trade P&L, taking into account the entry fee denominator. The rule sensitivity was based on the last session's open, a lagged 20-session mean of high-low, a stop of 1.25 ADR, and a target of 2 ADR. If these conditions were not met, the third session's close was used. The system was managed daily, with OHLC stops and ambiguity resolved by filling at the open, and targets were capped. A bootstrap of 10,000 complete calendar window means was run across four ETFs, not 332 independent trades. The results included confidence intervals and per-symbol statistics, saved to match the title. The verdict rejected live adoption when uncertainty, cost, or execution gates failed, and a positive point estimate alone was not enough for adoption. The sources of this information are https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
A frozen specification note, number 1344, was made by a provider. The provider adjusted the Systematic Investment Plan, or SIP, from September 8, 2016, to September 8, 2026. This adjustment happened every 2685 New York Stock Exchange, or NYSE, session for each Exchange-Traded Fund, or ETF. No data from 2010 to 2015 was provided. The training and testing of the system only included entries and exits within a certain partition. The holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, but trades that spanned boundaries were excluded. The system started with four independent cash sleeves, each with $250 in cash, and no leverage was used. There was no periodic rebalancing of cash across sleeves, and idle cash was set to 0. The system used Vectorbt to make explicit long-only orders, with a fee of 1 basis point, or 1bp, plus slippage of 5 basis points, or 5bp, per side. The raw cash return was reconciled with the Vectorbt trade profit and loss, or P&L, accounting for the entry fee denominator. The rule sensitivity was based on the last session's open price, the lagged 20-session mean of the high-low price, and a stop of 1.25 average daily range, or ADR, with a target of 2 ADR. If these conditions were not met, the system used the third session's close price. The system managed daily open-high-low-close, or OHLC, stops to avoid ambiguity, and adverse gap fills were capped at the target price. Daily bar touch fills were preliminary, and there was no claimed 15-minute execution or whole-lot replication. The system used bootstrapping with 10,000 complete calendar window means across four ETFs, not 332 independent trades. Confidence intervals, or CI, and per-symbol statistics were saved to match the observation title. The verdict rejected live adoption when uncertainty, cost, or execution gates failed. A positive point estimate alone was not enough for adoption. The sources for this information include a publication from Purdue University and a dataset from Aditya Perswal.
A frozen specification note, number 1344, was made by the provider. The provider adjusted the Systematic Investment Plan, or SIP, for all of 2016, starting on September 8, to 2026. This adjustment was made for every 2685 New York Stock Exchange, or NYSE, session for each Exchange-Traded Fund, or ETF. No data from 2010 to 2015 was provided. The training and testing of the system only included entries and exits within a certain partition. The holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, but trades that spanned boundaries were excluded. The system started with four independent cash sleeves, each with $250 in cash, and no leverage was used. The cash was not rebalanced periodically, and idle cash was set to $0. The Vectorbt system was used to make explicit long-only orders, with a fee of 1 basis point, or bp, plus slippage of 15 bp per side. The raw cash return was reconciled with the Vectorbt trade profit and loss, or P&L, accounting for the entry fee denominator. The rule sensitivity was based on the last session's open, the lagged 20-session mean of high and low, and a stop of 1 Average Daily Range, or ADR, with a target of 2 ADR. If these conditions were not met, the system used the third session's close. The system was managed daily, with open, high, low, and close, or OHLC, stops, and ambiguity was resolved by using the first stop. Adverse gap fills were made at the open, and target gaps were capped at the target. Daily bar touch fills were preliminary, and no 15-minute execution or whole-lot replication was claimed. A bootstrap of 10,000 complete calendar window means was made across four ETFs, not 332 independent trades. The confidence interval, or CI, and per-symbol statistics were saved, matching the title of the observation. The verdict rejected live adoption when uncertainty, cost, or execution gates failed. A positive point estimate alone was not enough for adoption. The source of this information includes a study on equity returns at the turn of the month from Purdue University and stock bar data from Aditya Perswal.
A frozen specification note1344 was made by the provider. The provider made an adjustment to the Systematic Investment Plan, which will be in effect from September 8, 2016, to September 8, 2026, and will be present for every 2685 New York Stock Exchange session for each Exchange-Traded Fund. However, no data from 2010 to 2015 was supplied. The training and testing of the system only included entries and exits within a certain partition, and the holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, excluding trades that span boundaries. The system started with four independent cash sleeves, each with $250, and no leverage was used. The Vectorbt system was used to make explicit long-only orders, with a fee of 1 basis point plus a slippage of 5 basis points per side. The rule sensitivity was based on the last session's open, the lagged 20-session mean of high and low, and a stop of 1 Average Daily Range and a target of 2 Average Daily Range. Other rules were also applied, such as managing daily high, low, open, and close stops, and filling gaps. The system did not claim to have 15-minute execution or whole-lot replication. A bootstrap analysis of 10,000 complete calendar window means was done across four ETFs, and the results were saved. The verdict was to reject live adoption when uncertainty, cost, or execution gates failed, and a positive point estimate alone was not enough for adoption. The sources of the information include a study on equity returns at the turn of the month from Purdue University and stock bar data from a website.
A frozen specification note1344 was made by the provider. The SIP adjustment includes all NYSE sessions from September 8, 2016, to 2026, for each ETF, but does not include data from 2010 to 2015. The train test only includes entries and exits within a partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, excluding boundary spanning trades. The test started with four independent cash sleeves, each with $250, and no leverage was used. There was no periodic rebalance between sleeves, and idle cash was set to 0. The vectorbt system was used with explicit long-only orders, a fee of 1 basis point, and slippage of 15 basis points per side. The raw cash return was reconciled with the VBT trade P&L, taking into account the entry fee denominator. The rule sensitivity was based on the last session's open, a lagged 20-session mean of high-low, a stop at 0.75 ADR, and a target at 2 ADR. If these conditions were not met, the third session's close was used. The system managed daily OHLC stops, with ambiguity resolved by using the first stop, and adverse gap fills were set to open, with target gaps capped. Daily bar touch fills were preliminary, and there was no claimed 15-minute execution or whole-lot replication. A bootstrap of 10,000 complete calendar window means was run across four ETFs, not 332 independent trades. The confidence interval and per-symbol statistics were saved, matching the title. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The sources used were https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
A frozen specification note, number 1344, was made by a provider. The provider adjusted the Systematic Investment Plan, or SIP, from September 8, 2016, to September 8, 2026. This adjustment was made for every New York Stock Exchange, or NYSE, session for each Exchange-Traded Fund, or ETF. No data from 2010 to 2015 was provided. The training and testing of the system only included entries and exits within a certain partition. The holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades. Trades that spanned boundaries were excluded. The system started with four independent cash sleeves, each with $250, and no leverage was used. The cash sleeves were not rebalanced periodically, and idle cash was set to 0. The system used Vectorbt, which is a backtesting library, to generate orders with an explicit long-only strategy, a fee of 1 basis point, and slippage of 5 basis points per side. The raw cash return was reconciled with the Vectorbt trade profit and loss, or P&L, accounting for the entry fee denominator. The rule sensitivity was based on the last session's open price, the lagged 20-session mean of the high and low prices, and a stop loss of 0.75 Average Daily Range, or ADR, and a target of 2 ADR. If these conditions were not met, the system used the third session's close price. The system managed daily high, low, open, and close, or OHLC, prices to stop ambiguity, adverse gap fills, and target gap caps. Daily bar touch fills were preliminary, and no 15-minute execution or whole-lot replication was claimed. The system used bootstrapping to generate 10,000 complete calendar window means across four ETFs, not 332 independent trades. The confidence interval, or CI, and per-symbol statistics were saved to match the title observation. The verdict rejected live adoption when uncertainty, cost, and execution gates failed. A positive point estimate alone was not enough for adoption. The source of this information includes a publication by McConnell and data from Aditya Perswal.
A frozen specification note, number 1344, was made. The provider made an adjustment to the Systematic Investment Plan, which includes all NYSE sessions from September 8, 2016, to 2026, for each exchange-traded fund, but does not include data from 2010 to 2015. The training and testing only include entries and exits within a certain partition, and the holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, excluding trades that span boundaries. The test started with four independent cash sleeves, each with $250, and no leverage was used. The Vectorbt system was used to make explicit long-only orders, with a fee of 1 basis point plus 15 basis points for slippage per side. The rule sensitivity was based on the last session's open price, a 20-session mean of high and low prices, and a stop loss of 0.75 average daily range and a target of 1.5 average daily range. A news scan found the headline of a study on equity returns at https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and stock bar data at https://runway.adityaperswal.workers.dev/data/stock-bars. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption.
A frozen specification note, number 1344, was made by a provider. This provider made an adjustment to the Systematic Investment Plan, which includes all NYSE sessions from September 8, 2016, to September 8, 2026, for each Exchange-Traded Fund, but does not include data from 2010 to 2015. The training and testing of the system only included entries and exits within a certain partition, and the holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, excluding trades that span boundaries. The system started with four independent cash sleeves, each with $250, and did not use leverage or periodic rebalancing, with idle cash set to 0. The system used Vectorbt to make explicit long-only orders, with a fee of 1 basis point plus slippage of 5 basis points per side. The system's rule sensitivity was based on the last session's open price, with a stop loss set at 0.75 times the average daily range and a target set at 1.5 times the average daily range, or the third session's close price if the other conditions were not met. The system managed daily high, low, open, and close prices, with stops and targets set first, and adverse gap fills set to open, with a capped target. The system did not claim 15-minute execution or whole-lot replication. A bootstrap analysis was done with 10,000 complete calendar window means across four ETFs, not 332 independent trades. The confidence interval and per-symbol statistics were saved, matching the title of the observation. The verdict rejected live adoption when uncertainty, cost, or execution gates failed, and a positive point estimate alone was not enough for adoption. The source of this information includes a study on equity returns at the turn of the month from Purdue University and stock bar data from a website.
This is a frozen specification note. The provider made a SIP adjustment from September 8, 2016, to 2026, for every NYSE session, for each ETF, but did not supply data from 2010 to 2015. The training and testing only included entries and exits within a certain partition. The holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, excluding trades that spanned boundaries. There were four independent cash sleeves, each initially worth 250 USD, with no leverage and no periodic rebalancing between sleeves, and idle cash was set to 0. The vectorbt system was used with explicit long-only orders, a fee of 1 basis point, and slippage of 15 basis points per side. The rule for the trail was to use the last session's open, a 20-session mean of high and low as a stop, and a target of 1.5 times the average daily range, or the third session's close if that did not apply. The system managed daily high, low, open, and close data to stop ambiguity and adverse gap fills, and capped the target if there was a gap. The trail was activated after a gain of 1 average daily range and updated the next day. This system did not claim to execute trades every 15 minutes, nor did it replicate whole lots or current market capitalization. A bootstrap analysis of 10,000 complete calendar window means was done across four ETFs, not 332 independent trades. The confidence interval and per-symbol statistics were saved to match the title of the observation. The verdict rejected live adoption when uncertainty, cost, or execution gates failed, and a positive point estimate alone was not enough to adopt the system. The sources for this information include a publication by McConnell from Purdue University and stock bar data from Aditya Perswal's website.
A frozen specification note, number 1344, was provided. The provider made a SIP adjustment from September 8, 2016, to September 8, 2026, and was present for every NYSE session for each ETF, but no data was supplied for 2010-2015. The training and testing only included entries and exits within a partition, and the holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated ETF trades, excluding boundary-spanning trades. There were four independent cash sleeves, each initially equal to 250 USD, with no leverage, no periodic cross-sleeve rebalance, and idle cash was set to 0. The Vectorbt system used explicit long-only orders, with a fee of 1 basis point plus slippage of 5 basis points per side, and the raw cash return reconciled with the VBT trade P&L accounting for the entry fee denominator. The rule trail was based on the last session's open, with a lagged 20-session mean high-low stop of 1 ADR and a target of 1.5 ADR, or otherwise the third session's close. The system managed daily OHLC stops to resolve ambiguity, with adverse gap fills opening and target gaps capped at the target, and the trail of 1 ADR was activated after a gain of 1 ADR and updated the next day, not every 15 minutes. Daily bar touch fills were preliminary, with no claimed 15-minute execution, nor whole-lot or current cap replication. A bootstrap of 10,000 complete calendar window means was performed across four ETFs, not 332 independent trades, and the confidence interval and per-symbol statistics were saved to match the title observation. The verdict rejected live adoption when uncertainty, cost, or execution gates failed, and a positive point estimate alone was not enough for adoption. The source of this information includes a study on equity returns at the turn of the month from Purdue University and stock bar data from Aditya Perswal.
This is a frozen specification note. The provider made an adjustment to the System Information Protocol, which includes all NYSE sessions from September 8, 2016, to 2026, for each exchange-traded fund, but no data from 2010 to 2015 is provided. The training and testing only include entries and exits within a certain partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, excluding trades that span boundaries. There are four independent cash sleeves, each initially worth 250 USD, with no leverage and no periodic rebalancing between sleeves, and idle cash is worth 0. The vectorbt system is used for explicit long-only orders, with a fee of 1 basis point plus 15 basis points for slippage per side. The cash return is reconciled with the trade profit and loss accounting, considering the entry fee denominator. The managed rule is based on the last session's open, with a stop at 1 average daily range and a target at 1.5 average daily ranges, lagged by 20 sessions, or the third session's close. The system manages daily high, low, open, and close prices, with stop-first ambiguity, adverse gap fills, and target gap capped targets. Daily bar touch fills are preliminary, with no claimed 15-minute execution or whole-lot replication. A bootstrap analysis is done with 10,000 complete calendar window means across four ETFs, not 332 independent trades. The confidence interval and per-symbol statistics are saved, matching the title. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The sources are https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
A frozen specification note1344 was made by the provider. The provider made an adjustment to the Systematic Investment Plan, which started on September 8, 2016, and will end on September 8, 2026. This adjustment is applied to every New York Stock Exchange session for each Exchange-Traded Fund, but no data from 2010 to 2015 is provided. The training and testing of the system only include entries and exits within a certain partition. A holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, but trades that span across boundaries are excluded. The system starts with four independent cash sleeves, each with $250, and no leverage is used. There is no periodic rebalancing of cash across sleeves, and idle cash is set to 0. The system uses a vectorized backtesting framework, which explicitly allows only long positions, with a fee of 1 basis point plus a slippage of 5 basis points per side. The system's cash return is reconciled with the trade profit and loss accounting, taking into account the entry fee denominator. The managed rule is based on the last session's open price, with a stop loss set at 1 Average Daily Range and a target set at 1.5 Average Daily Range, lagged by 20 sessions. If this rule is not met, the system uses the third session's close price. The system manages daily high, low, open, and close prices, with a stop loss set first, and ambiguity is resolved by using the open price. Adverse gap fills are capped at the target price. The system does not claim to have 15-minute execution, nor does it replicate whole lots or current capital. A bootstrap analysis is performed with 10,000 complete calendar window means across four ETFs, not 332 independent trades. Confidence intervals and per-symbol statistics are saved, matching the title of the observation. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The source of this information includes a publication from Purdue University and a dataset from Aditya Perswal.
A frozen specification note, number 1344, was made by a provider. The provider made an adjustment to the Systematic Investment Plan, which includes all sessions from September 8, 2016, to 2026, for each exchange-traded fund on the New York Stock Exchange. However, no data from 2010 to 2015 was provided. The training and testing of the system only included entries and exits within a certain partition. A holdout period from 2019 to 2025 had 83 complete calendar windows and 332 correlated trades, excluding trades that span boundaries. The system started with four independent cash sleeves, each with 250 US dollars, and no leverage was used. The cash was not rebalanced periodically, and idle cash was set to zero. The system used a vectorized backtesting library to make explicit long-only orders, with a fee of one basis point plus slippage of 15 basis points per side. A basis point is a unit of measurement, one hundredth of one percent. The system's cash return was reconciled with the trade profit and loss accounting, taking into account the entry fee. The rule for opening a trade was to open at the last session's open and close at the next month's third close. The system managed daily high, low, open, and close prices, with a stop-loss order to limit losses, and adverse gap fills were handled by opening at the next available price. A target gap was capped to limit potential losses. The system did not claim to execute trades at a specific 15-minute interval, nor did it replicate whole lots or current market capitalization. The system used a bootstrapping method to estimate the mean of 10,000 complete calendar windows across four exchange-traded funds, not 332 independent trades. Confidence intervals and per-symbol statistics were saved to match the observation title. The verdict rejected live adoption when uncertainty, cost, or execution gates failed. A positive point estimate alone was not enough for adoption. The sources of the information include a study on equity returns at the turn of the month from Purdue University and stock bar data from a website.
A frozen specification note1344 was made by the provider. The SIP adjustment was made for all sessions from September 8, 2016, to September 8, 2026, and includes every NYSE session for each ETF, but does not include data from 2010 to 2015. The training and testing only include entries and exits within a certain partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, and trades that span boundaries are excluded. There are four independent cash sleeves, each initially worth 250 USD, with no leverage and no periodic rebalancing between sleeves, and idle cash is worth 0 USD. The vectorbt system uses explicit long-only orders, with a fee of 1 basis point plus slippage of 5 basis points per side. The raw cash return is reconciled with the VBT trade P&L, taking into account the entry fee denominator. The rule for opening a position is to open at the last session's open and close at the next month's third close. The system manages daily OHLC stops to avoid ambiguity, fills open positions on adverse gaps, and caps target gaps. Daily bar touch fills are preliminary, and there is no claimed 15-minute execution or whole-lot replication. A bootstrap of 10,000 complete calendar window means was run across four ETFs, not 332 independent trades. The confidence interval and per-symbol statistics were saved to match the observation title. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The sources for this information are https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
A frozen specification note1344 was made. The provider made a SIP adjustment from September 8, 2016, to 2026, which includes every NYSE session for each ETF, but does not include data from 2010 to 2015. The training and testing only include entries and exits within a certain partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated ETF trades, and trades that span boundaries are excluded. There are four independent cash sleeves, each initially worth 250 USD, with no leverage and no periodic rebalancing between sleeves, and idle cash is worth 0. The vectorbt system uses explicit long-only orders, with a fee of 1 basis point plus 15 basis points for slippage per side. The raw cash return is reconciled with the VBT trade P&L accounting for the entry fee denominator. The rule for the parent is to use the close of the second-to-last session to predict the close of the third session of the next month. The system manages daily OHLC stops to avoid ambiguity, fills gaps at the open, and caps target gaps. Daily bar touches are used for preliminary fills, but there is no claim of 15-minute execution or whole-lot replication. A bootstrap of 10,000 complete calendar window means was done across four ETFs, not 332 independent trades. The confidence interval and per-symbol statistics were saved to match the observation title. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, and a positive point estimate alone is not enough for adoption. The sources used are https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf and https://runway.adityaperswal.workers.dev/data/stock-bars.
This is a frozen specification note. The provider made an adjustment to the System Information Protocol, which includes all sessions from September 8, 2016, to 2026, for every New York Stock Exchange session, for each exchange-traded fund, but does not include data from 2010 to 2015. The training and testing only include entries and exits within a certain partition. The holdout period from 2019 to 2025 has 83 complete calendar windows and 332 correlated trades, excluding trades that span boundaries. There are four independent cash sleeves, each initially worth 250 US dollars, with no leverage and no periodic rebalancing between sleeves, and idle cash is worth 0 dollars. The vectorbt system uses explicit long-only orders, with a fee of 1 basis point plus slippage of 5 basis points per side. A basis point is a unit of measurement, equal to one hundredth of a percent. The system reconciles raw cash returns with trade profit and loss accounting, considering the entry fee. The parent rule is based on the close of the second-to-last session and the close of the third session of the next month. The system manages daily high, low, open, and close prices, with stop-loss orders that are executed first in case of ambiguity, and adverse gap fills are capped. A stop-loss order is an order to sell a security when it falls to a certain price. The system does not claim to execute trades at a specific 15-minute interval, nor does it replicate whole lots or current market capitalization. The system uses a method called bootstrapping, which involves resampling with replacement, to estimate the mean of 10,000 complete calendar windows across four exchange-traded funds, not 332 independent trades. The system saves confidence intervals and per-symbol statistics, matching the title of the observation. The verdict rejects live adoption when uncertainty, cost, or execution gates fail, meaning that a positive point estimate alone is not enough for adoption. The source of this information includes a research paper from Purdue University and a dataset from a website.
A news scan found a note about a test of a managed trend. The test started with eight fixed exchange-traded fund, or ETF, sleeves, each with an initial investment of 1250 USD. These sleeves were managed independently, with cash reinvested and equal initial weights that could drift over time without monthly rebalancing. A position was entered at the next session's open if the prior month's closing return was positive, with no short selling or leverage used. The first stop loss was set at the prior 20-day mean high-low, with a target of 2 times the risk, or 2R. If the prior high plus 1R was reached, the next day's entry was set at breakeven. An adverse stop priority or gap at open was also set, with a conservative target fill. No reentry was allowed in the same month, and the last session of each month was liquidated. The test was trained on data from 2017 to 2020, with a holdout period from 2021 to 2025, and an extension from January to August 2026. A warm-up period was used in 2016, with no invented early history. Fees were set at 1 basis point, or bp, plus slippage of 15bp on each side of a trade. The results were as follows: in 2021, the return was -3.1982894279861673, in 2022 it was -1.1115754020214585, in 2023 it was -2.4559342553208685, in 2024 it was -2.571763853282849, and in 2025 it was -1.0573886480381267. These results are simulated portfolio returns, not actual account returns, and only include completed trades. The data used does not account for 15-minute venue exits, gap overshoot, or National Best Bid and Offer, or NBBO, and does not include fixed business costs. The ETF adjustment means all returns are proxy data, not futures excess returns, inverse-vol scale, or original long-short paper replication. The era used in this test was reused from prior research and is not untouched prospective evidence. The conclusion is to reject venue-style transfer, with fixed variants reported without selecting the best. The source of this information includes https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all and https://w4.stern.nyu.edu/facdir/lpederse/papers/TimeSeriesMomentum.pdf, as well as QTR9090200 research/trend.py and archived results.
This is a description of a test for a managed trend. The test started with eight fixed exchange-traded fund, or ETF, sleeves, each with an initial investment of 1250 USD. The cash from these investments was reinvested independently, and the initial weights were equal, but they were allowed to drift over time without being rebalanced monthly. A new investment was made at the start of the next session if the return from the previous month was positive. The test did not use short selling or leverage. The first stop-loss was set at the average high and low prices of the previous 20 days, with a target of 2 times the risk. If the price reached a new high plus 1 times the risk, the next day's entry price was set to break even. If there was a large gap at the open, the stop-loss was prioritized. The target was filled conservatively. The test did not allow reentry in the same month, and all positions were liquidated at the end of the month. The test was trained on data from 2017 to 2020, and the results from 2021 to 2025 were used as a holdout. The warm-up period was 2016, and no early history was invented. The fees were 1 basis point, or bp, plus 5 bp for slippage on each side of the trade. The results were calculated using a long-only strategy from orders that matched an independent event cash ledger. The results for each year were as follows: 2021 had a return of -1.4266879110777175, 2022 had a return of 0.03282691161201612, 2023 had a return of -1.5404086082613566, 2024 had a return of -0.8817272924663944, and 2025 had a return of 1.1059498552612235. These results are simulated portfolio returns, not actual account returns. The test only included completed trades and did not include partial current month trades. The daily open, high, low, and close prices, or OHLC, and marks did not identify 15-minute venue exits, gap overshoot, or national best bid and offer, or NBBO. The test used fractional sizing and did not include fixed business costs. The ETF adjustment meant that all returns were proxy data, not futures excess returns, inverse-vol scale, or original long-short paper replication. The era used in the test was reused from prior research and was not new, prospective evidence. The conclusion was to reject venue-style transfer, and fixed variants were reported without selecting the best. The sources for the test were https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all and https://w4.stern.nyu.edu/facdir/lpederse/papers/TimeSeriesMomentum.pdf, as well as QTR9090200 research/trend.py and archived results.
This is a description of a test managed trend for QTR9090200. The test has the following parameters: a target of 1.5 and a cost of 16 basis points. Here are the details: 1. The test started with eight fixed exchange-traded fund sleeves, each with an initial investment of 1250 USD, and cash was reinvested independently in each sleeve. The initial weights of the sleeves were equal, but they were allowed to drift over time without monthly rebalancing. A new position was entered at the next session's open if the previous month's close return was positive. The test did not use short selling or leverage. A stop-loss was set at the prior 20-day mean high-low, with a target of 1.5 times the risk. If the prior high plus 1 times the risk was reached, the next day's breakeven point was set. An adverse stop priority or gap at the open was also used, with a conservative target fill. The test did not allow re-entry in the same month, and the last session of each month was liquidated. 2. The test was trained on data from 2017 to 2020, with a chronological holdout period from 2021 to 2025, and an extension from January to August 2026. The warm-up period was 2016, with no invented early history. Fees were 1 basis point plus slippage of 15 basis points on each side. The vectorbt long-only strategy matched the independent event cash ledger from orders. 3. The results of the test are as follows: the returns for the years 2021, 2022, 2023, 2024, and 2025 were -3.2927516767092824, -0.9664546669718388, -2.139692711344532, -2.815434596853883, and -1.7076777646982344, respectively. These results are simulated portfolio returns, not actual account returns, and only completed trades are included. The test used daily open-high-low-close data and marks, but did not account for 15-minute venue exits, gap overshoot, or national best bid and offer prices. Fractional sizing was used, and there were no fixed business costs. The ETF adjustment means that all returns are proxy data, not futures excess returns, inverse-volatility scale, or original long-short paper replication. The era used in the test was reused from prior research and is not untouched prospective evidence. The conclusion is to reject venue-style transfer, and fixed variants are reported without selecting the best. The sources of the data are https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all and https://w4.stern.nyu.edu/facdir/lpederse/papers/TimeSeriesMomentum.pdf, and the test was run using QTR9090200 research/trend.py and archived results.
A news scan found the headline about QTR9090200 test managed trend 378 target 1.5 cost 6.000000000000001 basis points. The test has two main parts. First, eight fixed exchange-traded fund sleeves started with 1250 USD each and reinvested cash independently. They had equal initial weights, but these weights changed over time because there was no monthly rebalancing across sleeves. The test entered the market at the next session's open if the prior month's return was positive, without using shorts or leverage. It used a stop-loss at the prior 20-day mean high-low, with a target of 1.5 times the risk. If the price reached the prior high plus 1 times the risk, the next day's entry would be at breakeven. The test prioritized stopping losses over filling targets at the open and had a conservative target fill. It did not reenter the market in the same month and liquidated at the end of each month. Second, the test trained on data from 2017 to 2020, held out data from 2021 to 2025, and extended the test from January to August 2026. It used a warm-up period in 2016 and did not invent any missing early history. The fees were 1 basis point plus 5 basis points for slippage on each side of the trade. The results matched the cash ledger and were long-only, meaning the test only bought and never sold short. The results for the years 2021 to 2025 were -1.526994698235573, 0.17326654036462497, -1.2198998112890935, -1.131832654620768, and 0.4228545307626952, respectively. These results are simulated portfolio returns, not actual account returns, and only include completed trades. The test used daily open, high, low, and close prices and did not account for 15-minute venue exits, gap overshoot, or national best bid and offer prices. It also did not include fixed business costs or fractional sizing. The returns are proxy data and not excess returns from futures or original long-short paper replication. The era used in the test was reused from prior research and not new evidence. The conclusion was to reject transferring the results to a different venue and to report fixed variants without selecting the best. The sources for the test include https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all and https://w4.stern.nyu.edu/facdir/lpederse/papers/TimeSeriesMomentum.pdf, as well as QTR9090200 research and archived results.