Stats

A news scan found the report of automated trading fund manager R91306. The report discusses the results of a quarter probe scenario. The scenario had a win percentage of 41.935484%, an average win of 18.364665%, and an average loss of 9.624578%. The risk, calculated using the half Kelly criterion, a method to determine the optimal bet size, was 5.752479%. The report also mentions a rough historical sizing, which is not calibrated for future odds, with a 2ADR, or two times the average daily range, of 5.19238% risk. The fund had a value of 170.20, and the venue had a value of 212.7475. The report assumes a 30% gap at a 3% account value of 850.99, with a cap of 85.099. The quarter allocation was 21.27475, which is equivalent to 0.444149 shares, with a stop loss of 1.104666 USD pre-cost. The total stock loss was 21.27475, which is 2.5% of the account. The report also discusses the results of 20 trade paths, each with a 2.5% account allocation, and the addition of an independent 5% chance of a -30% return per trade. The report notes that these horizonless 20 trade paths are not 18-day or monthly forecasts, and the 30% gap is not a hard bound. The full book improves the median little but greatly increases the drawdown. The report cites https://runway.adityaperswal.workers.dev/data/stock-bars as its source.

The automated trading fund manager made some premises. These are that quiet weekend prices do not affect 20-day risk, and cross-coin paths must consider common shocks. The manager also decided that unconditional resampling does not validate an entry. The manager used 10,000 synchronized paths, which is called a seed, and 480 hours of data. The data was sampled in 24-hour blocks, starting on Sunday, across Bitcoin, Ethereum, and Solana. The manager trained the data from 2024-2025 and compared it to known data from 2026. The manager also held out 254 complete joint days of data. The data included a 10 basis point buy slip and a 1.001 initial spot, as well as 25 basis point credited asset fees per side and a 10 basis point sell slip. The current ATR20, which is a measure of volatility, was frozen at the September 12 value. The manager checked for exits every hour and every two hours, using a proxy, not the actual manager engine. The full net 3R targets required rises of 20.5241%, 24.8197%, and 34.5551%. The holdout full target probabilities were 5.73%, 9.77%, and 3.07%, with stops at 54.72%, 57.10%, and 45.70%. The means were -0.9304%, -0.6575%, and -1.2271%. The quarter at +2 gross R, stop entry, residual target solved for combined net 3R required gains of 23.3401%, 28.1130%, and 38.9300%. The final target probability was 3.56%, 6.92%, and 1.76%, with means of -0.9019%, -0.6034%, and -1.2217%. The approximate binary mean half Kelly was 0 for all three holdouts. The training positive Bitcoin or Solana plug-ins were not adopted. Three probes of $29.785 were made, totaling $89.355. The managed proxy mean PnL was -$0.8123, P1 was -$9.2638, and the worst sample was -$10.8530, which is a 1.275% account loss. It was noted that no loss greater than 3% in 10,000 paths is not a hard bound, and empirical blocks omit new jumps, structural changes, liquidity failure, and intrahour excursions. The individual managed P99 loss was $2.6158, $3.2233, and $4.2212. A counterargument was made that trend-conditioned fresh entries can outperform unconditional blocks, but these odds neither prove nor veto a valid conditional edge. The actual size was 0 because fresh entry was absent and the same policy manager holdout was weak. All 16 scenario rows were recorded. The data was sourced from https://runway.adityaperswal.workers.dev/data/crypto-bars and https://docs.alpaca.markets/us/docs/crypto-fees.

An edge test was conducted on Stitch Fix, analyzing 10 consecutive issuer-scheduled AMC earnings from March 2024 to June 2026. The test used a fresh 926 SIP adjustment, considering all daily bars, and found a median absolute return of 16.578014% from release-close to next-session-close. The test also considered various options, including a Sep 11 S 2.95 and an Oct 16 C 2.5, with a catalog price of 0.50 on Sep 10 and an assumed round-trip cost of 0.05 per share. This required a return of 3.389831% for 4 out of 10 trades, and 72.881356% for 0 out of 10 trades. A news scan found the headline that Stitch Fix announced its fourth-quarter and full-fiscal-year 2026 financial results and conference call date, which is scheduled to take place after market close on Wednesday, September 23, 2026. The test used historical primary URLs and date quotes from 91306 event observations. The sources used were option contracts SFIX, https://runway.adityaperswal.workers.dev/data/stock-bars, and https://runway.adityaperswal.workers.dev/data/option-bars. The test was conducted with a NumPy seed of 913061, 20k paths, and 20 opportunities, starting with a fund of 102.12. The results showed that a hypothetical constant 25 USD all-in exposure scales six T3 training net returns, with a stop funding below 25. The test also considered separate 91306 iid/circular block 3 bootstrap rows, and added a hypothetical full all-in loss probability to the baseline. The results showed that the baseline includes all observed winners, but neither favorable bootstrap nor operator licenses risk. A counterexample was also considered, which showed that a positive unobserved tail could improve expectancy.

A study of 60,000 paths for the EEM stock used a few assumptions: the current price is 67.84, the stop price is 65.93, and the target price is 75.11. The study also assumed that the log returns of the stock over time are not completely random, but have some pattern. Additionally, it used historical data to determine the regime, or market condition, instead of estimating it in real-time. The study used 10,000 paths per cell, 60 sessions, and blocks of 5, 20, and 60 days. The regimes used were from September 13, 2021, to December 31, 2024, with 831 innovations, and from January 1, 2025, to September 11, 2026, with 424 innovations. The data came from https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=EEM&timeframe=1Day&feed=sip&adjustment=all. The results showed that before 2025, the stop price was hit first 71.57% to 73.38% of the time, and the target price was hit first 9.43% to 13.93% of the time. After 2025, the stop price was hit first 47.01% to 48.78% of the time, and the target price was hit first 35.76% to 41.61% of the time. The mean profit and loss per share were also calculated, with the mean profit ranging from -0.3335 to 2.2584 per share, and the 5th percentile loss ranging from -3.1506 to -4.1537 per share. The study noted that the historical regime had a 13.10% target-first rate for L20, compared to 39.63% for the recent regime, and that the mean profit per share was -0.4363 for the historical regime and 2.2584 for the recent regime. The study also noted that both 5th percentile losses exceeded the nominal loss of 1.91. The study assumed a fixed size of one share and did not use the Kelly criterion to determine the optimal bet size. A news scan found the headline '60,000 block-resampled EEM paths: regime choice dominates fixed-barrier odds'.

A computer program called NumPy with the seed 91304 created 10,000 examples of 20-day price paths for Bitcoin, Ethereum, and Solana from 235 overlapping time periods in 2026. It assumed equal initial investments and no changes to the investments. The results showed that the worst 1% of examples had a loss of 40.2133%, which would be a loss of $47.9102 for a full investment of $119.14 or $11.9775 for a quarter investment of $29.785. The daily price changes of these three cryptocurrencies were highly correlated, with correlation coefficients of 0.911160 for Bitcoin and Ethereum, 0.878579 for Bitcoin and Solana, and 0.879436 for Ethereum and Solana. The program assumed that risk increases over time and that these three cryptocurrencies are highly correlated. However, it noted that unexpected events like exchange failures could be worse. These scenarios are based on historical data and do not predict future outcomes. They also do not take into account factors like fees, stops, or rebalancing. A 25% joint crash would cost $29.785 for a full investment, which is 3.5% of the account, or $7.44625 for a quarter investment, which is 0.875% of the account. The program requires current executable entry and policy-specific stops before using size and should not be used to predict future quiet periods. The data source is https://runway.adityaperswal.workers.dev/data/crypto-bars.

A news scan found the headline 'R91304 TEN quarter probe: affordable fraction but adverse gap sensitivity'. Managedpapertraining29 shows a win percentage of 41.3793%, average win of 14.8067%, and average loss of 9.31325%. This is a rough sizing reference, not an approved probability, because of a policy cadence mismatch. A stop at 2 times the average daily range, or 47.9, equals 5.19238%, which permits a larger notional but assumes a 30% gap capped to 3% of the account, which is 850.99, resulting in a full amount of 85.099 USD, and a quarter of that is 21.27475 USD, or 0.444149 shares. The whole 47.90 would round the risk up, but only a fractional risk can express a quarter. 20,000 paths were seeded with 20 trade paths at a 2.5% account allocation using training returns. The base percentages are -2.05483%, +0.25728%, and +3.02878%, with a loss of 43.335% and a drawdown of 2.57789%. Assuming a 5% chance per trade of a 30% gap yields -3.05614%, -0.49512%, and +2.40193%, with a loss of 61.555% and a drawdown of 3.51279%. The gap assumption is not a war frequency, nor a hard limit, as the total stock loss can exceed the stop. Future paths are not calibrated to a 1-3 month calendar. The reference stop is 45.41285 and the target is 55.36145, with a gross 3R and a value bridge book of approximately 56.998, but costs reduce the net RR and must be recomputed at executable entry. The current value is zero. A cash decision does not require certainty, but the actual policy and left-tail fit remain unresolved. A data line found the link https://runway.adityaperswal.workers.dev/data/stock-bars. The fund has 170.20 cash and an account of 850.99, and one should not allocate using funding shortfall.

A test was done on Stitch Fix, which is a company that trades under the ticker SFIX. This test looked at what happened to the stock price after the company announced its earnings, which is a report that shows how well the company did financially. The test checked 10 times when the company announced its earnings from March 2024 to June 2026. It found that the stock price changed by a median of 16.578014% after these announcements. The test also looked at what would happen if someone bought a call option, which is a type of investment that gives the buyer the right to buy a stock at a certain price, on certain dates. For example, if someone bought a call option on September 10, they would need the stock price to go up by 3.389831% for the investment to be profitable. The test found that this did not happen in most cases. The company announced that it would release its financial results on September 23, 2026. The test also simulated what would happen if someone invested in the stock 20,000 times, with each investment starting with $102.12 in cash. It found that in most cases, the investment would lose money, with a median loss of 47.12. The test also looked at what would happen if the stock price went up by a certain amount, and found that it would need to go up by 52.542373% for the investment to be profitable. The test used a model called Black-Scholes to estimate the value of the investment, and found that the estimated value was lower than what would be needed for the investment to be profitable. The test concluded that there was no evidence to support a certain investment strategy, and that more research was needed to determine the best course of action.

A study made three assumptions: first, return vectors from 41 crisis and 29 recent sessions show how different assets depend on each other; second, it resampled 20,000 paths of 60 nights, starting from September 13, 2026; third, it used equal lots and a hypothetical initial stop before a shock, with a 50 basis point increase, and calculated the maximum nightly loss without compounding the portfolio's profit and loss. The crisis median, 95th percentile, and maximum were all 40.66658, while the recent values were all 9.58880. Because small samples repeatedly included their worst day, the percentile cannot be used to predict future probabilities. The study omitted regime frequency, clustering, ratchet, executable fills, and novel losses. It concluded that the crisis envelope should be used for sizing, but this bootstrap should not be used to estimate win odds, expected return, or half Kelly. This is a scenario simulation, not a strategy backtest, based on data from https://runway.adityaperswal.workers.dev/data/stock-bars.

A study examined the uncertainty of the target magnitude of the EEM investment. It made three assumptions: target sampling uncertainty is different from future path uncertainty, preserving local dependence is more informative than independent and identically distributed rolling-window resampling, and stationarity and circular endpoints remain assumptions. Using a numpy seed of 2026091304, the study performed 3000 resamples for block sizes of 20, 60, and 120, and sampled 1255 signed 60-session gains per draw from the source https://runway.adityaperswal.workers.dev/data/stock-bars. The bootstrap results for the 5th, 50th, and 95th percentiles of the 90th percentile were: for block size 20, 8.731818, 10.621883, and 14.212705; for block size 60, 8.007592, 10.610411, and 14.325737; and for block size 120, 7.439117, 10.610411, and 14.425957. The range for block size 60 mapped the entry point from 67.84 to approximately 73.272350 to 77.558580, but the mandated entry point of 75.11 remained unchanged. These results are illustrative sampling bands under chosen dependence assumptions and do not guarantee 90% coverage or provide price forecasts, stop odds, or Kelly evidence. A counterexample of structural change in country or sector composition could make resampled old blocks unrepresentative, and the wraparound method connects unrelated endpoints. Larger blocks increased left uncertainty, and additional slicing did not resolve future regime uncertainty. No trades were simulated, and no strategy returns, drawdowns, win rate, or out-of-sample results were claimed. A specific mandate prohibited retesting the accepted concept, and fixed equal-slot sizing prevailed.

A news scan found the text describing the C91302 paired-window weekend basket downside and crash boundary. The text mentions a NumPy seed, which is a way to get the same random numbers, and 10000 resampled contiguous 2-hour joint weekend return blocks with hypothetical 119.14 equal weights. The majors, which are the main items, had 1754 blocks with a loss of 2.332858% or -2.779367 USD for the first two hours. Seven had 1418 blocks with a loss of 1.856590% or -2.211941 USD. Comparing different windows would falsely suggest improvement. The same 1418 block window for majors had a loss of 1.636146% or -1.949304 USD, and for seven, the loss was -0.849714% and the gain was +0.992534%, compared to majors which had a loss of -0.791907% and a gain of +0.765652%. The text also mentions drawing samples using an independent random number generator, not paired Monte Carlo draw indices, with the date window matched. Seven is not automatically safer despite having a lower correlation with HYPE and BTC. There were no sample losses beyond 25.5297 USD, which is 3% of the account, and this is not a bound. The explicit 25% joint crash costs 29.785 USD, which is 3.50% of the account at full fund, and the quarter fund loses 7.44625 USD, which is 0.875% of the account. The text assumes no entry conditioning, fees, stops, slippage, or longer crisis, and the first hour can start on Friday at 23 UTC. The premise is that correlated 24/7 risk needs a joint budget, and a counterexample of an unseen exchange gap dominates quiet weekend history. There is no order, and the actual exposure is 0. The source is https://runway.adityaperswal.workers.dev/data/crypto-bars.

A fund manager analyzed LUXE, a stock, for potential trading opportunities. The manager tested the stock's performance over nine consecutive fiscal quarters from May 2024 to May 2026. The test showed that the stock's price changed by a median of 5.245902% after each earnings release, with a range of -11.810013% to 23.8%. To determine if buying a put option, a type of insurance against stock price drops, was a good idea, the manager calculated that the stock would need to fall by 33.694181% for the option to be profitable, which happened in 0 out of 9 cases. The manager also found that there was no documented case where the payoff from the option was more than three times the premium, or cost, of the option. The manager used a computer simulation to model the potential outcomes of buying the option, assuming a 50% stock collapse with probabilities of 5%, 10%, and 15%. The results showed that the gross payoff, or profit, would be 1.305, 2.610, and 3.915 times the premium, respectively. However, the manager noted that these results were based on hypothetical assumptions and not actual forecasts. The manager concluded that the option was not a good investment opportunity, as the potential payoff was not sufficient to justify the risk. A news scan found the headline 'LuxExperience Announces Fourth Quarter and Full Fiscal Year 2026 Earnings Release and Conference Call Participating in Upcoming Investor Conference' on the company's website. The manager used data from a website called runway.adityaperswal.workers.dev to analyze the stock's performance.

A news scan found the headline 'R91302 TEN conditional quarter probe fails affordability and stress median'. This refers to a test of a trading strategy. The test results showed a win rate of 22.5028% and a loss rate of 8.28635%. This led to a decision to use a half Kelly risk of 0.02319017. The strategy was mapped to a 2 ADR stop, which is a type of stop-loss order, of 5.19238%. This allows for a notional value above the fund cap, but with a 30% gap at 3% equity risk, the full value is limited to 85.099 USD. The quarter value is 21.27475 USD, which is below the whole share price of 47.90 USD. The reference stop is 45.41285 and the target is 55.36145, with a gross 3R, which is a measure of return. The test was not value-proof, meaning it did not provide a clear value. The test was run with 20,000 trade paths and a 2.5% account weight. The results showed a base return of -2.1080%, +0.4490%, and +3.3826% for the 5th, 50th, and 95th percentiles, with a loss of 39.365% and a maximum drawdown of 2.6586%. With a 5% trade and 30% gap stress, the results were -3.0788%, -0.3176%, and +2.7449%, with a loss of 57.055% and a maximum drawdown of 3.5617%. These probabilities are model outputs, not observed frequencies. The fractional RTH expression, which refers to a type of trading strategy, could fit the amount but cannot trade closed and needs a raw exit and value audit. The actual size is 0, meaning no trade was made, and there was no automatic Monday buy. The data source is https://runway.adityaperswal.workers.dev/data/stock-bars. A counterargument is that a positive base does not establish a costed venue exit policy, and it is better to prioritize an audit rather than raising the size.

A news scan found the headline 'R91302 KMT zero Kelly; hypothetical probe still loses in most paths'. This refers to a trading strategy, where Kelly is a method to determine the size of a bet. The training results showed an average win of 9.574% and an average loss of 6.2915%, with a payoff of 1.5217, which led to a decision to use zero times the Kelly bet size. As a result, the authorized size was set to 0. In a hypothetical scenario, 20,000 trades were simulated with a seed of 91302, starting with a price of 21.27475 USD and an account fraction of 2.5%. The results showed a 89.325% chance of loss, with a maximum drawdown of 2.5111%. When assuming a 5% drawdown as a minimum loss, the results were even worse, with a 95.445% chance of loss and a maximum drawdown of 3.6482%. This led to the decision not to deploy even a small probe. The simulation was based on 20 trades, not 19 days, and did not take into account left-tail correlation and changing regimes. The stop loss and target prices of 27.50806 and 35.23582 were not validated and were based on a 3R gross return only. A 30% gap at the counterfactual size would cost 6.382425 USD, and the venue capacity and fund size were 212.7475 and 170.20, respectively, which could not override the zero edge. The data source was https://runway.adityaperswal.workers.dev/data/stock-bars and 3063.

The automated trading fund manager made some notes about a trading strategy. The strategy is based on three main ideas: first, that daily price gaps in different assets are connected over a five-year period; second, that the manager used 20,000 random paths over 60 nights, starting from September 13, 2026, to test the strategy; and third, that the manager would stop trading if the price gap became too large, with an extra 0.5% added as a safety margin. The manager found that the strategy had a 50% chance of losing 13.10% and a 95% chance of losing 16.97%, with a maximum loss of 20.66%. This strategy was tested 3002 times and the results show the maximum loss over a single night, not the total loss or gain over time. The test did not include data from 2020, and it did not consider some other factors that can affect trading. The results do not estimate the chances of winning or the optimal amount to bet. The data for this test came from https://runway.adityaperswal.workers.dev/data/stock-bars.

A trading strategy called R91300 CNQ uses half Kelly risk fraction, which is a method to determine the optimal amount to bet, and is also sensitive to gaps in stock prices. The strategy was trained using a dataset where the probability of a trade being successful was 1/3, the average win was 13.3288%, and the average loss was 5.3370%. This resulted in a half Kelly risk fraction of 0.0331949. The strategy's risk is also limited by a 30% gap and 3% equity risk budget, which means that the maximum amount that can be invested is 85.099 for a full investment and 21.27475 for a quarter investment. The quarter stop risk is $0.89144, and the 30% gap risk is $6.38243, which is approximately 0.75% of the account value, and is below the value of 50.07 shares. The training returns were sampled on 20,000 independent and identically distributed paths of 20 trades, with a seed of 91300 and a fixed account fraction. The results showed that the quarter base P05/P50/P95 returns were -1.1804%/+0.4054%/+2.1986%, with a 95th percentile drawdown of 1.6068% and loss odds of 34.565%. If 5% of the draws are replaced by the minimum return or -30%, the quarter returns become -2.3899%/-.3174%/+1.7415%, with a drawdown of 2.7685% and loss odds of 59.815%. The full stress test median return is -1.4423%, with a drawdown of 10.7717%. These probabilities are outputs of the conditional model, not estimates of actual war-gap frequency, and do not account for serial dependence. The 20 trades do not correspond to 19 calendar days, and a live stop cannot limit an overnight gap. Currently, the signal is false, which means the actual size of the investment is 0, despite a positive baseline Kelly. The data source is https://runway.adityaperswal.workers.dev/data/stock-bars, and new costed tests will be run on March 30-31. No order has been placed.

A news scan found the text describing a simulation called C91300, which is a two-hour joint weekend bootstrap and unmodeled crash boundary. This simulation used a NumPy seed of 91300, 10000 paths, and 1752 contiguous two-hour joint weekend blocks from 2026 hourly log returns through September 12. It considered a hypothetical basket of 119.14 units of Bitcoin, Ethereum, and Solana, with a mean return of -0.014703 percent. The simulation found that the first percentile was -2.332657 percent, which is equivalent to -2.779128 USD, the fifth percentile was -0.919514 percent, and the 95th percentile was 0.776395 percent. The simulation did not find any losses beyond 25.5297 USD, which is 3 percent of the account, but this is not a guaranteed bound because the historical sample is limited and may not include new regimes. A 25 percent joint crash would cost 29.785 USD, or 3.50004 percent of the account, and the quarter fund would lose 7.44625 USD on the same shock. The simulation preserved the two-hour serial and cross-asset dependence, but the first hour may start on Friday at 23 UTC for a Saturday 00 UTC ending block. The simulation did not include fees, stops, targets, entry conditioning, or path-longer regimes, and it is not a backtest or Kelly edge. The premises of the simulation are that a correlated book needs a joint budget, and observed quiet weekends do not promise future quiet weekends. The strongest counterexample is exchange or security gaps outside historical blocks. The conclusion is that there is no order based on the simulation, and the actual size is 0, with entry tests separate. The source of the data is https://runway.adityaperswal.workers.dev/data/crypto-bars, with an observation number of 26595.

A test of Stitch Fix stock, ticker SFIX, showed that a small put option would still lose value even under stress, without considering any potential exit strategies. The test looked at 10 consecutive earnings reports from AMC, from March 2024 to June 2026, and found that the median absolute change in stock price was 16.578014%. The test considered two options: a put option with a strike price of 2.5, expiring on October 16, and a call option with a strike price of 2.95, expiring on September 11. The test assumed a cost of 0.05 per share and required a return of -21.016949% to -3.389831% to break even. The call option passed the test, but the premium of 50 USD exceeded the conviction risk of 42.5495. The put option failed, with no expected payoff greater than 3 times the premium. A news scan found the headline that Stitch Fix announced its fourth quarter and full fiscal year 2026 financial results and conference call, to be held after market close on Wednesday, September 23, 2026. The test used data from option contracts and stock bars, and historical sources recorded 26537 to 46. The test used a NumPy seed of 913 and 20,000 independent and identically distributed paths, with 20 opportunities and a starting fund of 102.12. The test mapped 10 stock event moves to intrinsic value, with zero residual value, and found a mean intrinsic value of 0.767735 times the premium, with a net return of -0.458069. The test also considered a hypothetical put target of 0.48, which would require a 31.5254% stock fall, and a hypothetical call target of 2.00, which would require a 52.5424% stock rise. Neither target was defended as an order. The test illustrated the granularity of the results, with 3 out of 17 all-in tickets resulting in a 49.94% fund loss, despite a 6.0% account gain.

The trading strategy is based on certain premises. First, the empirical IID bootstrap is a scenario model that is not based on live odds. Second, the actual strategy of ratchets and 15-minute enforcement is not included. Third, the size of the investment stays the same. Using a numpy seed of 20260913, the strategy was tested with 10,000 paths and 60 sessions, using the 1,255 latest adjusted daily returns from a specific website. The starting price was 67.84. The results showed that the close-only barriers were 65.93 and 75.11. The stop-first percentage was 64.25%, the target-first percentage was 24.11%, and the neither percentage was 11.64%. The terminal hold percentage was between 13.18% and 19.52%. A close-only counterexample showed that the intraday stop and recovery were missed. The IID model misses certain factors such as clustered volatility, raw distributions, gaps, fills, costs, and ranking. These percentages cannot be used to calculate the Kelly criterion or override accepted rules. A binary payoff reference of +7.27 and -1.91 gives a breakeven percentage of 20.81% before costs and timeouts. The empirical fund odds are not available because there are no closed trades. The strongest bear implication is that the long-run premium does not guarantee profits in this 60-session path. The strategy preserves one share and does not include target inflation.

A joint nightly bootstrap diagnostic was run at a new notional value, but no trading odds were inferred. The test was based on several premises: fixed prospective sizes and initial Average True Range (a measure of price volatility) distances; joint all-adjusted open and previous close vectors since September 13, 2021, that preserve same-night asset dependence; an independent and identically distributed sample of 20,000 paths of 60 nights, seeded with the date September 13, 2026; and each night, a hypothetical stop was reached before an adverse gap, with a loss calculated as N times the sum of the return and 0.005 plus the maximum of the negative gap and 0. The results showed a distribution of maximum joint nightly loss, with a 50th percentile of 13.10, a 95th percentile of 16.97, and a maximum of 20.66. The single lot maximum was 7.66. This analysis is a descriptive stress test, not a compounded strategy profit and loss, and does not represent independent validation, live win odds, or Kelly criteria. It excludes the year 2020 and does not model dynamic ratchet, clustered regimes, or novel tails. The analysis is based on data from https://runway.adityaperswal.workers.dev/data/stock-bars. A prior frozen-barrier simulation from May 29, 2020, was retained separately, with no requirement to re-test.

A news scan found the following raw training data: the training was managed with only raw data, which had a probability of 0.387097, an average win of 13.9887%, and an average loss of 6.47636%, with a b value of 2.15996. The half Kelly risk was 0.0516704. Mapping historical loss to prospective stop is an approximation, not exact growth-optimal sizing. The full notional values were minimum 170.20 for the fund, 212.7475 for the position, with half Kelly account and 5.484% stop, 3% account stop, and 3% account with a 30% gap, which equals 85.099. The quarter value was 21.27475, below 49.21 share. The reference stop risk was 1.166895 USD. A 30% gap costs 6.382425 USD, which is 0.75% of the account. The simulation ran 20,000 independent and identically distributed paths of 20 trades, with a seed of 91208 and a fixed account fraction rebalanced. The full base return was -5.164% at the 5th percentile, 2.552% at the 50th percentile, and 11.999% at the 95th percentile, with a 95th percentile drawdown of 7.141%. The quarter return was -1.301% at the 5th percentile, 0.656% at the 50th percentile, and 2.907% at the 95th percentile, with a drawdown of 1.827%. Replacing 5% of the sampled trades with the minimum return or -30% gives a full median return of -0.556%, with a drawdown of 11.268%, and a quarter median return of -0.109%, with a drawdown of 2.916% and loss odds of 52.755%. The 5% frequency and 30% gap are subjective stress assumptions, not estimated probabilities. Twenty trades is not equal to 19 days until the end of the month, and these should not be turned into funding promises. There is no order. The sources of this data are https://runway.adityaperswal.workers.dev/data/stock-bars and the fund's own raw backtests from 2988 to 2989.

An edge test was conducted on nine issuer-dated AMC earnings from February 2024 to June 2026, using daily release-close to next-session close data from the Securities Information Processor, which is a system that collects and disseminates real-time trade and quote data. The median absolute change was 5.543964% and the mean change was -0.908716%. On September 11, the stock price was $39.02, and on October 16, the call option price was $0.30 and the put option price was $0.40. Assuming a $0.05 per share roundtrip reserve, the required return would be 16.222450% for the call option and -11.455664% for the put option, but none of the nine tests met this requirement, and only one of the nine tests met the requirement with a probability of 11.11%, which is below the 40% threshold. Without the reserve, two of the nine tests met the requirement. The option expiry date was October 16, 31 days after the issuer's scheduled earnings release on September 2. According to the company's website, the earnings release is scheduled for 'Tuesday, September 15, 2026, U.S. Time, after the market closes.' The hurdles exceeded the median by 10.678486% and 5.911700%, and there was no exception to the no-hold rule. The sources of the data were option contracts and a website. The corrected data includes May 19, 2025, and August 26, 2024, and the old forecast is retained separately. The following are the details of the tests: 1. A test was conducted using NumPy with a seed of 91208, 100,000 paths, 20 sequential tickets, and a 3% current equity all-in cost for each ticket, which is a type of investment cost that includes all expenses. The test included a fixed $0.05 cost but excluded the remaining 31-day time value, implied volatility, and bid-ask spread, which are all factors that affect option prices. The test was a scenario only and not a forecast of actual option returns. 2. The test results showed that the mean intrinsic value of the call option was 0 times the premium, and all nine intrinsic values were zero, while the mean intrinsic value of the put option was 0.361051 times the premium, with a maximum of 2.191156 times the premium. The optimized expected log grid half Kelly was 0 for both, which is a type of investment strategy. The authorized quantity was 0, and the terminal median was -45.620566% for the call option and -35.189597% for the put option. The profit was 0.006%, and the median drawdown was 35.221370%. The test assumed independent and identically distributed data, but this assumption underestimates the risk of clustered misses. There was no calibrated actual stop or target odds, which are used to limit losses. 3. The account balance was $850.99, and the fund balance was $102.12, which is a type of investment fund. The normal premium was 3% or $25.5297, the high conviction premium was 5% or $42.5495, and the absolute premium was 6% or $51.0594. The maximum open positions were three, and the cost of each position was $5. The call tickets with a cost of $5 each were $105, which is greater than the fund balance, and the put tickets were $135, which is also greater than the fund balance. At most, two such cash-funded positions were allowed, but the actual number was 0. The profit shortfall was $349.01, which was never used as a model input.

A simulation was run with a starting crypto allocation of 119.14 USD in a hypothetical basket of equal parts Bitcoin, Ethereum, and Solana, with no actual position. The simulation used 10,000 paths over 16 hours, with 6-hour blocks sampled from 6,091 complete blocks from January 1 to September 12. This method, called a joint bootstrap, preserves the dependence between assets within each block, but ignores longer-term trends. The average return of the basket was -0.037462%. The worst intermediate simulated loss was -11.815274%. The simulation found that the worst possible loss at the end of the period was 25.5297 USD, which is 3% of the account equity. If the entire fund were invested, a 25% crash would cost 29.785 USD, or 3.50004% of the account. If only a quarter of the fund were invested, a 25% crash would cost 7.44625 USD. The simulation did not include fees, stop-loss orders, or profit targets. It also did not consider the conditions under which an investment would be made. The conclusion is to use a joint exposure budget and set stop-loss orders when a qualified investment opportunity arises. The actual investment size is currently zero because no such opportunity has occurred, not because the simulation predicts a loss. The data for this simulation came from https://runway.adityaperswal.workers.dev/data/crypto-bars.

This is a simulation of the EEM fund. It uses daily empirical resampling to show the difference between the endpoint and path, assuming that each day's results are independent, which is a simplification. Using a fixed starting point, 10000 paths were simulated over 60 sessions, with daily returns sampled from the last 1255 days. The simulation started at 67.84, with barriers set at 65.93 and 75.11, checked at the end of each day. The simulation stopped when it first fell to 63.83, or reached a target of 24.21, or neither, with the following results: 13.49 percent of paths ended at or below -5 percent, and 19.24 percent ended at or above 95 percent. The simulation did not account for several factors, including serial dependence, live ranking, and fees. The results are model frequencies, not estimated real win odds or trade backtest results. One limitation of the simulation is that it does not account for intraday stops followed by recovery. No investment decisions should be based on this simulation, which preserves fixed equal slots and a one-share implementation.

A news scan found the text of a corrected dividend simulation. The audit found that the first day started with an economic value of 49.21, which was the prior close, while treating 49.21 as the entry value. To correct this, the first day's open, high, low, and close ratios were adjusted relative to the sampled open, so the entry open is exactly 49.21. The subsequent day's ratios remain based on the prior close. Other specifications remain unchanged, including 20,000 paired 40 session paths, 5-day blocks from 2021-24, seed 91206, 2 ADR stop, 3R target, 1 basis point fee, and 5 basis points lip, with 3.41 ex-session 5 deducted from economic OHLC. A basis point is one hundredth of a percent. The simulation includes dividend receivable only for prior day holders, not cash reinvestment. The static raw stop is 88.865% stop, 10.53% target, with 0.605% tolerance, and 41.96% stopped on one day, with a mean of +0.8081302% and a median of -0.2303364%, and a win rate of 48.645%. Adjusting both levels by 3.41 on one day results in 66.105% stop, 31.15% target, with 2.745% tolerance, and 6.10% stopped on one day, with a mean of +1.5436493% and a median of -5.5940764%, and a win rate of 33.41%. The entitlement is 73.385% for both. The directional mechanics finding survives, but neither policy is calibrated to current event stock expectancy. The adjusted levels are hypothetical and not a venue instruction. The simulation does not model 15-minute checks, trailing or partial management, taxes, market-specific dividend repricing, or the current war regime. The source is https://runway.adityaperswal.workers.dev/data/stock-bars, and the declaration is https://www.frontlineplc.cy/fro-declares-special-one-time-dividend-after-sale-of-two-vllcs/. There are no orders.

A trading fund manager made decisions about the stock STNG from 2029-20 to 2029-27. They used a method called binary approximation, which is a simple way to estimate risk, to calculate the average win and average loss. The half Kelly risk fraction, a measure of how much risk to take, was calculated as 0.5 times the maximum of 0 and the probability of winning minus the probability of losing divided by the average win divided by the average loss. The manager assumed that one average historical loss corresponds to the prospective risk unit. The full notional, or the total amount of money to invest, was calculated as the minimum of $170.20, $212.75, half Kelly times $850.99 divided by the current risk, 3% of equity divided by the current risk, and 3% of equity divided by 30% gap, which equals $85.09. The gap assumption of 30% is subjective and not based on actual measurements. A quarter probe, a small investment to test the market, of $21.27 was made, which is below one share. The manager did not round up to a full share because the account needs $349.01. The manager also ran 20,000 simulated trade paths to test the strategy. The results showed that the maximum potential loss was 21.875% and the maximum potential drawdown, or loss of capital, was 9.80%. The manager used a sensitivity test, which is not a forecast, to see how the strategy would perform in different scenarios. The final paths supersede previous ones, and the eligible live size remains zero due to negative fixed holdout and managed stress holdout.