Sign up

Quantellect Insider Cluster Buys — v1

890 fills over 2,512 sessions · Oct 3, 2016 – Sep 30, 2026 · 5-stock equal weight, monthly · fills at the next open, 5 bps per side

Not available yet · Details and notifications
QBacktest by Quantellect·Results through Sep 30, 2026·Published Oct 8, 2026, 4:28 PM ET·Version 1 of this strategy · engine bw-portfolio-2
● DEVELOPMENT BACKTESTNext-open fills · 5 bps per sideDaily split-adjusted prices · dividends excluded9 retained research runsReference replay · reconciled

REPORT HISTORY

publication time in ET · each version and its original fills remain readable
v1 · CURRENTInitial

Results through Sep 30, 2026
Published Oct 8, 2026, 4:28 PM ET

Measured historical result: +$270,401 net equity gain, +270.4% net return, 51.1% win rate, 1.21 profit factor, and −55.36% maximum drawdown from Oct 3, 2016 through Sep 30, 2026. Backtests describe historical results and do not predict future results.

Quantellect Insider Cluster Buys looks for stocks with multiple qualifying off-plan insider purchases in the configured recent window. Each monthly review uses the latest available event snapshot, applies the minimum cluster requirement, and ranks eligible names by cluster size under the pinned default rule. The five highest-ranked stocks form an equal-weight target basket, with portfolio changes modelled at the following session's open. Holdings use whole split-adjusted shares and may remain overnight through later reviews. The strategy is long-only and uses no leverage, short sales, stop-loss, or terminal liquidation. Event records use their qualified public-availability dates; trading-plan status can be incomplete, and dividends and cash interest are excluded. This page is the full backtest report for that strategy: performance, uncertainty ranges, drawdowns, stability by year, and a fill-by-fill trade log.

⚠ Development backtest. The rules were chosen on the same history they were tested on; the historical periods were not kept untouched for a final independent test. This report (v1) does not provide sealed-holdout or prospective paper results: no sealed historical holdout has been registered, and prospective paper trading has not started for this strategy. Every statistic below carries its uncertainty range, concentration and stress scenarios so fragility is visible, not just the headline.

PERFORMANCE

net · next-open fills, 5 bps per side · 2,512 sessions incl. warm-up in cash
NET EQUITY GAIN+$270,401includes the final value of positions still held · net profit from sales, after allocated costs: $297,013.65
WIN RATE51.1%225W / 215L of 440 sales
PROFIT FACTOR1.21$1692.2k / $1395.2k gross from sales
EXPECTANCY+$675per sale
AVG WIN+$7,521225 winning sales
AVG LOSS−$6,489215 losing sales
MAX DRAWDOWN−55.36%a $77,974.70 loss · peak Feb 27, 2017, trough Mar 23, 2020 · recovered Jul 28, 2020 · 860 sessions peak to recovery (88 from the trough)
WIN STREAK14consecutive winning sales, in order
LOSS STREAK9consecutive losing sales, in order
WORST DAY−$80,591close-to-close portfolio value change, incl. unsold holdings
WORST MONTH−$115,506calendar-month portfolio value change, incl. unsold holdings
TIME IN MARKET97.5%median closed-position hold 21 sessions

Initial value $100,000.00 · final value $370,401.18 · return +270.40% · CAGR 14.04% (252-session annualised). The largest dollar drawdown is a separate episode: $229,004.65 (38.21%) from Nov 9, 2021 to Sep 30, 2026, not yet recovered at the end of the window. Net equity gain and net profit from sales use different totals; the difference is not printed as an open-position profit.

EQUITY & DRAWDOWN

cumulative equity gain in dollars · drawdown from peak in percent · same time axis
Cumulative equity gain and drawdown2,512 daily observations from 2016-10-03 through 2026-09-30. Cumulative equity gain ends at 270401.18 dollars; the lower line shows percentage drawdown from each previous peak.$500k$400k$300k$200k$100k$0drawdown from peak (percent)0%−10%−20%−30%−40%−50%−60%2017201820192020202120222023202420252026+$270,401Cumulative equity gain and drawdown2,512 daily observations from 2016-10-03 through 2026-09-30. Cumulative equity gain ends at 270401.18 dollars; the lower line shows percentage drawdown from each previous peak.$500k$400k$300k$200k$100k$0drawdown from peak (percent)0%−10%−20%−30%−40%−50%−60%20172019202120232025+$270,401

Shaded band: the largest percentage fall, 55.36% (a $77,974.70 loss) from the Feb 27, 2017 peak to the Mar 23, 2020 trough, recovered Jul 28, 2020: 860 sessions from the peak, 88 from the trough. The largest dollar fall is a separate episode: $229,004.65 (38.21%) from Nov 9, 2021, not yet recovered at the end of the window. Rearranging blocks of observed daily returns, 60.7% of the rearranged historical paths show a maximum fall at least as deep as the observed one.

DISTRIBUTION & RISK

5,000-resample day-block rearrangement · profit concentration

Daily portfolio return distribution 2,512 sessions · median 0.00% · 63 flat sessions out of 2,512

15
78
125
372
649
691
331
156
63
32
< −5%−5% to −3%−3% to −2%−2% to −1%−1% to 0%+0% to +1%+1% to +2%+2% to +3%+3% to +5%> +5%

Buckets, left to right: < −5% · −5% to −3% · −3% to −2% · −2% to −1% · −1% to 0% · +0% to +1% · +1% to +2% · +2% to +3% · +3% to +5% · > +5%

Uncertainty rearranged blocks of observed daily returns · 5,000 paths · blocks of 20 sessions

Range of full-period returns from the rearranged historical paths (95%)+-67.3% to +7030.1%
Share of rearranged paths with a positive return83.5%
Share with a drawdown at least as deep as the observed one60.7%
95th-percentile simulated drawdown95% of the rearranged historical paths have a maximum fall no larger than this−83.5%
Expected shortfall (mean of the worst 5% of daily returns)−4.08% per day
Gross profit / gross loss from sales$1,692,201.64 / −$1,395,187.99

These describe the historical sample; they are not forecasts or a chance of future success.

P5−2.61%
P25−0.94%
MEDIAN0.00%
MEAN+0.09%
P75+0.90%
P95+2.68%

Profit concentration the most profitable sale dates — all sales on a date added together; only positive date totals

Top 1 date67.6% · 1 removed · without: $96,193.25
Top 3 dates111.6% · 3 removed · without: $-34,584.89
Top 5 dates147.9% · 5 removed · without: $-142,274.28
Top 10 dates225.5% · 10 removed · without: $-372,897.32

Shares are of net profit from sales after allocated costs ($297,013.65); they can exceed 100%. Removing a date is arithmetic attribution, not a rerun. Net from sales stays positive at every removal threshold, down to $-372,897.32 with the 10 best dates removed.

STABILITY

rolling edge · breakdowns with sample-size disclosure · time split

Rolling profit factor over the last 20 sales 421 points · 19 points above PF 10 are drawn at the top edge (highest 98, from windows with almost no losses)

PF 1PF 2PF 4PF 6PF 8PF 1020172018202020212022202420252026
A fading edge shows here first. Descriptive only: the line is the profit factor of each window of 20 consecutive sales, in order; the dashed line is PF 1 (gross profit equal to gross loss).
YEARSALESNETWIN%SAMPLE
20164+$24,300100%<20
201745+$6,98856%20+ observations
201840−$3,28445%20+ observations
201943−$17,02547%20+ observations
202044+$270,02059%20+ observations
202142+$188,22164%20+ observations
202246−$117,51046%20+ observations
202348+$8,60452%20+ observations
202447+$51,47453%20+ observations
202547−$65,67040%20+ observations
202634−$49,10644%20+ observations
WEEKDAYSALESNETWIN%SAMPLE
Monday173+$386,36156%20+ observations
Tuesday77+$103,91655%20+ observations
Wednesday68−$113,71641%20+ observations
Thursday58−$105,54340%20+ observations
Friday64+$25,99655%20+ observations

weekday is set by the rebalance calendar

HOLDING TIMECLOSED POSITIONSNETWIN%SAMPLE
1–21 sessionsup to about 1 month255+$105,61153%20+ observations
22–63 sessionsabout 1 to 3 months134+$172,84346%20+ observations
64–126 sessionsabout 3 to 6 months7+$51,02186%<20
127–252 sessionsabout 6 to 12 months4−$32,4620%<20
253+ sessionsover a year0+$0Undefined<20

fully closed positions by duration band, first purchase to full sale; open positions excluded

Time-split stability (fixed rules; not a sealed holdout) At least one half non-positive

The same fixed rules applied to the two halves of the window. This is not a sealed holdout: the second half was not kept untouched for a final independent test.

FIRST HALF · Oct 3, 2016 – Sep 28, 2021 · 1,256 sessions
+444.83%RETURN
40.51%CAGR
−55.36%MAX FALL
1.30DAILY PF
SECOND HALF · Sep 29, 2021 – Sep 30, 2026 · 1,256 sessions
−32.01%RETURN
-7.45%CAGR
−38.21%MAX FALL
0.95DAILY PF
Returns by period years, months, rolling windows — select to expand

YEARS

PERIODSESSIONSRETURNMAX FALLPF
201663+30.94%−3.68%2.81
2017251+1.29%−18.95%1.01
2018251−15.63%−24.86%0.88
2019252+10.19%−26.96%1.08
2020253+245.97%−49.96%1.59
2021252+36.29%−14.07%1.24
2022251−24.89%−36.18%0.82
2023250+20.69%−23.51%1.13
2024252−10.21%−15.09%0.91
2025250−3.28%−18.18%0.98
2026187−19.07%−21.32%0.81

MONTHS

PERIODSESSIONSRETURNMAX FALLPF
2016-1021+0.00%−0.00%Undefined
2016-1121+28.30%−2.90%5.27
2016-1221+2.06%−3.68%1.25
2017-0120−0.66%−5.85%0.93
2017-0219+3.98%−4.66%1.28
2017-0323−1.53%−8.28%0.86
2017-0419+1.50%−4.17%1.10
2017-0522−11.93%−11.93%0.29
2017-0622+4.94%−7.11%1.44
2017-0720−2.77%−7.56%0.81
2017-0823−4.16%−5.19%0.56
2017-0920+4.93%−3.08%1.83
2017-1022+5.69%−3.74%1.52
2017-1121+2.75%−3.29%1.39
2017-1220−0.03%−2.05%1.00
2018-0121−0.92%−3.48%0.85
2018-0219−2.62%−4.75%0.80
2018-0321−0.50%−5.38%0.94
2018-0421−0.06%−2.28%0.99
2018-0522+2.59%−2.69%1.31
2018-0621+0.63%−5.07%1.05
2018-0721−0.72%−5.46%0.90
2018-0823+4.90%−2.42%1.74
2018-0919−2.42%−5.46%0.78
2018-1023−9.72%−13.76%0.57
2018-1121+2.91%−5.67%1.26
2018-1219−9.78%−17.61%0.51
2019-0121+9.49%−1.80%2.90
2019-0219+9.35%−4.73%1.91
2019-0321−1.34%−6.74%0.89
2019-0421−0.11%−2.84%0.99
2019-0522−17.49%−17.49%0.18
2019-0620+0.86%−7.70%1.07
2019-0722+1.92%−4.33%1.32
2019-0822−4.87%−7.79%0.71
2019-0920+0.94%−8.72%1.05
2019-1023+3.53%−2.66%1.49
2019-1120+2.19%−1.30%1.70
2019-1221+8.39%−2.48%1.99
2020-0121−6.71%−8.47%0.43
2020-0219−8.81%−13.01%0.47
2020-0322−27.66%−40.36%0.58
2020-0421+37.16%−17.79%1.85
2020-0520+3.97%−15.63%1.13
2020-0622+5.64%−13.94%1.20
2020-0722+177.37%−27.01%2.50
2020-0821+7.86%−5.02%1.69
2020-0921−4.42%−7.25%0.69
2020-1022+2.73%−8.72%1.14
2020-1120+14.61%−1.45%4.69
2020-1222+10.82%−2.03%3.02
2021-0119+3.00%−4.36%1.39
2021-0219+6.23%−4.09%1.64
2021-0323+6.74%−8.66%1.47
2021-0421+5.28%−0.99%2.37
2021-0520+4.58%−5.24%1.51
2021-0622−2.82%−5.27%0.67
2021-0721−3.45%−12.15%0.81
2021-0822+1.31%−3.53%1.20
2021-0921+2.30%−5.05%1.17
2021-1021+8.65%−1.08%4.04
2021-1121−3.67%−6.86%0.70
2021-1222+4.13%−6.31%1.25
2022-0120−19.87%−22.82%0.20
2022-0219−0.31%−7.61%0.98
2022-0323+3.35%−5.44%1.27
2022-0420−11.69%−13.87%0.40
2022-0521−4.41%−12.43%0.77
2022-0621−7.04%−12.63%0.60
2022-0720+12.03%−4.18%2.27
2022-0823−3.15%−8.67%0.81
2022-0921−2.68%−6.48%0.73
2022-1021+12.48%−4.14%2.42
2022-1121−1.69%−5.00%0.84
2022-1221−0.72%−5.35%0.93
2023-0120+13.93%−2.48%2.84
2023-0219−0.47%−3.66%0.94
2023-0323−10.18%−13.37%0.55
2023-0419−1.50%−5.46%0.88
2023-0522−7.56%−8.77%0.60
2023-0621+16.21%−2.36%2.67
2023-0720+10.73%−3.82%2.37
2023-0823−12.27%−15.87%0.35
2023-0920−10.95%−11.31%0.19
2023-1022+3.92%−5.36%1.30
2023-1121+8.94%−3.56%2.14
2023-1220+14.34%−3.42%2.61
2024-0121−2.30%−3.18%0.69
2024-0220−3.47%−5.77%0.77
2024-0320+3.97%−3.06%1.50
2024-0422−6.94%−8.65%0.47
2024-0522+12.44%−5.52%2.68
2024-0619+0.17%−3.71%1.02
2024-0722+0.08%−0.00%Undefined
2024-0822+0.05%−7.24%1.00
2024-0920−3.90%−7.59%0.69
2024-1023−9.77%−9.77%0.49
2024-1120+7.94%−3.00%1.94
2024-1221−6.78%−8.05%0.51
2025-0120−2.67%−5.22%0.74
2025-0219−1.73%−5.41%0.82
2025-0321−3.85%−7.75%0.73
2025-0421−2.95%−8.74%0.85
2025-0521+10.44%−4.35%2.04
2025-0620−0.84%−6.86%0.92
2025-0722+5.45%−3.71%1.42
2025-0821+2.56%−3.81%1.32
2025-0921−7.30%−9.79%0.53
2025-1023−3.74%−7.24%0.80
2025-1119+1.21%−6.37%1.10
2025-1222+1.31%−6.59%1.10
2026-0120−4.53%−6.90%0.67
2026-0219+0.65%−7.51%1.04
2026-0322−3.06%−9.00%0.78
2026-0421−1.66%−5.10%0.86
2026-0520−3.95%−10.78%0.76
2026-0621−5.93%−7.36%0.60
2026-0722+2.30%−5.64%1.22
2026-0821+2.44%−0.00%Undefined
2026-0921−6.70%−7.18%0.44

ROLLING 12 MONTHS

PERIODSESSIONSRETURNMAX FALLPF
2016-10-03 – 2017-09-29251+22.16%−18.95%1.14
2016-11-01 – 2017-10-31252+29.11%−18.95%1.17
2016-12-01 – 2017-11-30252+3.40%−18.95%1.03
2017-01-03 – 2017-12-29251+1.29%−18.95%1.01
2017-02-01 – 2018-01-31252+1.02%−18.95%1.01
2017-03-01 – 2018-02-28252−5.39%−18.57%0.96
2017-04-03 – 2018-03-29250−4.41%−18.57%0.96
2017-05-01 – 2018-04-30252−5.88%−15.54%0.95
2017-06-01 – 2018-05-31252+9.64%−11.00%1.08
2017-07-03 – 2018-06-29251+5.13%−11.00%1.05
2017-08-01 – 2018-07-31252+7.35%−7.56%1.07
2017-09-01 – 2018-08-31252+17.50%−7.56%1.16
2017-10-02 – 2018-09-28251+9.27%−7.56%1.08
2017-11-01 – 2018-10-31252−6.66%−15.52%0.94
2017-12-01 – 2018-11-30252−6.51%−15.52%0.94
2018-01-02 – 2018-12-31251−15.63%−24.86%0.88
2018-02-01 – 2019-01-31251−6.76%−24.86%0.95
2018-03-01 – 2019-02-28251+4.70%−24.86%1.04
2018-04-02 – 2019-03-29251+3.81%−24.86%1.03
2018-05-01 – 2019-04-30251+3.76%−24.86%1.03
2018-06-01 – 2019-05-31251−16.55%−24.86%0.89
2018-07-02 – 2019-06-28250−16.36%−24.67%0.89
2018-08-01 – 2019-07-31251−14.14%−24.67%0.90
2018-09-04 – 2019-08-30250−22.13%−25.85%0.84
2018-10-01 – 2019-09-30251−19.45%−26.96%0.87
2018-11-01 – 2019-10-31251−7.63%−26.96%0.95
2018-12-03 – 2019-11-29250−8.28%−26.96%0.94
2019-01-02 – 2019-12-31252+10.19%−26.96%1.08
2019-02-01 – 2020-01-31252−6.11%−26.96%0.95
2019-03-01 – 2020-02-28252−21.70%−25.28%0.83
2019-04-01 – 2020-03-31253−42.58%−53.14%0.74
2019-05-01 – 2020-04-30253−21.16%−52.37%0.88
2019-06-03 – 2020-05-29251−0.64%−49.96%1.00
2019-07-01 – 2020-06-30253+4.08%−49.96%1.02
2019-08-01 – 2020-07-31253+183.24%−49.96%1.53
2019-09-03 – 2020-08-31252+221.11%−49.96%1.58
2019-10-01 – 2020-09-30253+204.04%−49.96%1.50
2019-11-01 – 2020-10-30252+201.70%−49.96%1.46
2019-12-02 – 2020-11-30252+238.37%−49.96%1.54
2020-01-02 – 2020-12-31253+245.97%−49.96%1.59
2020-02-03 – 2021-01-29251+281.98%−47.85%1.61
2020-03-02 – 2021-02-26251+344.95%−40.36%1.65
2020-04-01 – 2021-03-31252+556.47%−27.94%1.76
2020-05-01 – 2021-04-30252+403.89%−27.94%1.78
2020-06-01 – 2021-05-28252+406.83%−27.94%1.79
2020-07-01 – 2021-06-30252+366.23%−27.94%1.73
2020-08-03 – 2021-07-30251+62.29%−14.07%1.37
2020-09-01 – 2021-08-31252+52.44%−14.07%1.34
2020-10-01 – 2021-09-30252+63.16%−14.07%1.37
2020-11-02 – 2021-10-29251+72.57%−14.07%1.48
2020-12-01 – 2021-11-30252+45.04%−14.07%1.31
2021-01-04 – 2021-12-31252+36.29%−14.07%1.24
2021-02-01 – 2022-01-31253+6.03%−25.14%1.04
2021-03-01 – 2022-02-28253−0.50%−25.14%1.00
2021-04-01 – 2022-03-31253−3.66%−26.26%0.98
2021-05-03 – 2022-04-29252−19.19%−29.28%0.88
2021-06-01 – 2022-05-31253−26.13%−35.48%0.83
2021-07-01 – 2022-06-30252−29.34%−38.10%0.82
2021-08-02 – 2022-07-29251−18.01%−38.10%0.89
2021-09-01 – 2022-08-31252−21.62%−38.10%0.87
2021-10-01 – 2022-09-30252−25.43%−38.10%0.84
2021-11-01 – 2022-10-31252−22.81%−38.10%0.85
2021-12-01 – 2022-11-30252−21.22%−37.62%0.86
2022-01-03 – 2022-12-30251−24.89%−36.18%0.82
2022-02-01 – 2023-01-31251+6.79%−24.61%1.05
2022-03-01 – 2023-02-28251+6.63%−24.61%1.05
2022-04-01 – 2023-03-31251−7.33%−24.61%0.95
2022-05-02 – 2023-04-28250+3.36%−18.19%1.02
2022-06-01 – 2023-05-31251−0.06%−22.24%1.00
2022-07-01 – 2023-06-30251+24.93%−22.24%1.15
2022-08-01 – 2023-07-31251+23.49%−22.24%1.16
2022-09-01 – 2023-08-31251+11.86%−22.24%1.07
2022-10-03 – 2023-09-29250+2.36%−22.29%1.01
2022-11-01 – 2023-10-31251−5.43%−23.51%0.97
2022-12-01 – 2023-11-30251+4.80%−23.51%1.03
2023-01-03 – 2023-12-29250+20.69%−23.51%1.13
2023-02-01 – 2024-01-31251+3.50%−23.51%1.03
2023-03-01 – 2024-02-29252+0.37%−23.51%1.00
2023-04-03 – 2024-03-28249+16.18%−23.51%1.11
2023-05-01 – 2024-04-30252+9.77%−23.51%1.06
2023-06-01 – 2024-05-31252+33.53%−23.51%1.22
2023-07-03 – 2024-06-28250+15.10%−23.51%1.11
2023-08-01 – 2024-07-31252+4.03%−23.42%1.04
2023-09-01 – 2024-08-30251+18.64%−12.70%1.16
2023-10-02 – 2024-09-30251+28.02%−11.22%1.21
2023-11-01 – 2024-10-31252+11.16%−13.71%1.08
2023-12-01 – 2024-11-29251+10.14%−15.09%1.08
2024-01-02 – 2024-12-31252−10.21%−15.09%0.91
2024-02-01 – 2025-01-31251−10.55%−15.49%0.91
2024-03-01 – 2025-02-28250−8.93%−17.82%0.93
2024-04-01 – 2025-03-31251−15.78%−23.38%0.87
2024-05-01 – 2025-04-30250−12.17%−27.05%0.91
2024-06-03 – 2025-05-30249−13.73%−27.05%0.89
2024-07-01 – 2025-06-30250−14.60%−26.72%0.88
2024-08-01 – 2025-07-31250−10.02%−26.72%0.93
2024-09-03 – 2025-08-29249−7.76%−26.69%0.94
2024-10-01 – 2025-09-30250−11.03%−23.72%0.92
2024-11-01 – 2025-10-31250−5.09%−22.87%0.97
2024-12-02 – 2025-11-28249−11.01%−22.47%0.92
2025-01-02 – 2025-12-31250−3.28%−18.18%0.98
2025-02-03 – 2026-01-30250−5.13%−16.42%0.97
2025-03-03 – 2026-02-27250−2.84%−16.42%0.98
2025-04-01 – 2026-03-31251−2.05%−18.51%0.99
2025-05-01 – 2026-04-30251−0.75%−18.51%1.00
2025-06-02 – 2026-05-29250−13.68%−23.17%0.91
2025-07-01 – 2026-06-30251−18.11%−25.90%0.89
2025-08-01 – 2026-07-31251−20.55%−25.64%0.86
2025-09-02 – 2026-08-31251−20.64%−25.43%0.85
2025-10-01 – 2026-09-30251−20.13%−23.24%0.86

Counts are labelled: the year and weekday tables count sales (each sale once, including partial sales); the holding-time table counts fully closed positions. SAMPLE flags "20+ observations" or "Fewer than 20" — a disclosure threshold, not proof of reliability. Daily PF is the sum of positive daily dollar changes divided by the absolute sum of negative ones.

EXECUTION TIMING

study TIMING-01 · all fills moved to one time of day · all times ET
OPEN — 9:30 AM ET target
+210.70% return

Final equity $310,703 · 672 fills over 1,919 sessions. +35.31 percentage points vs the open-fill baseline. 17 of 689 decisions not executed for lack of a printed bar. Median simulated fill delay 0 min · 4.2% outside the exact order minute · 672 of 689 checks had a bar.

MIDDAY — 12:00 PM ET target
+176.34% return

Final equity $276,338 · 651 fills over 1,919 sessions. +0.95 percentage points vs the open-fill baseline. 34 of 685 decisions not executed for lack of a printed bar. Median simulated fill delay 0 min · 40.2% outside the exact order minute · 651 of 685 checks had a bar.

NEAR CLOSE — official close − 30 min
+174.61% return

Final equity $274,608 · 681 fills over 1,919 sessions. −0.78 percentage points vs the open-fill baseline. 10 of 691 decisions not executed for lack of a printed bar. Median simulated fill delay 0 min · 26.0% outside the exact order minute · 681 of 691 checks had a bar.

Qualified common window: Feb 12, 2019 – Sep 30, 2026 · 1,919 sessions. This study moves buys and sells together; it does not separately identify the best time to buy and the best time to sell.
Full-window open vs next close (separate comparison): +270.40% vs +299.18%; next close +28.78 percentage points vs open · Oct 3, 2016 – Sep 30, 2026 · 2,512 sessions.
Vendor-wide minute-data gaps included in the card counts: NVDA Jun 10, 2024 – Jul 22, 2024; TSLA Aug 1, 2023 – May 1, 2024. Simulated orders are placed at [09:30 ET / 12:00 ET / 30 minutes before the official close]. Each order uses the open of the first observed one-minute bar starting at or after the order time, strictly less than 30 minutes later and strictly before the official close. If no bar is observed in that window, the order is not executed: the strategy keeps its existing position or cash until its next scheduled rebalance and does not search for a later bar. An invalid first observed bar fails the run. Decisions that could not be executed for lack of a printed bar: open N of M, midday N of M, near close N of M, where M counts every name the strategy held or selected at each rebalance in that arm. Where the vendor supplied no minute data for a liquid name over a span of sessions, that span is listed here and is included in these counts; a missing vendor bar does not mean no trade printed. Differences between arms reflect both the time of day and which decisions could be executed from the minute data available, and the holdings that followed. Median simulated fill delay and the share of simulated fills outside the exact order minute are shown per card, together with common dates and actual fill completeness. These bar opens are execution proxies, not guaranteed next-trade prices or full-size fills. Thinly traded names may experience additional delay, wider spreads and slippage not captured by this simulation.

CAPITAL & EXPOSURE

average exposure 97.4% of capital · gross traded notional $68,102,091 · 19.9× annual one-way turnover
MEDIAN POSITION VALUE$84,929each positive holding valued at rebalance opens
MEAN POSITION VALUE$78,849same basis
MAX POSITION VALUE$519,425largest single holding at a rebalance open
MAX CONCURRENT POSITIONS5observed · target 5
MEDIAN CLOSED-POSITION HOLD21 sessions400 fully closed positions; 5 still open at the end, shown separately
OVERNIGHT RISKHeld overnightmonthly rebalance

ROBUSTNESS

recomputed under worse assumptions, never one collapsed score
SCENARIOADJUSTMENTREALIZED NET P&LΔ REALIZED NET VS BASE
BaseSaved default result; exact frozen-selection replay matched every fill, rebalance, daily mark, and metric.+$297,014—
Commission stressA 0.10% fee on each buy and each sell, replacing the base 0.05% per-side fee.+$259,807−$37,207
Slippage stressEvery modelled fill moved $0.01 against the strategy on the same split-adjusted price basis.+$232,829−$64,185
Commission and slippage stressBoth stated stress assumptions applied in one deterministic rerun.+$201,786−$95,228
Ten most profitable sale dates removedArithmetic removal of the ten largest positive execution-date sale totals; not a reinvested counterfactual.−$372,897−$669,911

Realized net P&L is net profit from sales, after allocated costs. Net equity gain includes the final value of positions still held. This table counts profit and loss from sales, after allocated costs, so it uses a different total. Stress rows retain the frozen default selections, calendar, whole-unit sizing, and valuation series. Independent reference implementation: the saved reference calculation was checked against this result under the stated rules — 119 of 119 ranked baskets matched, and 890 fill quantities and 2,512 daily marks matched in the independent replay. The reference's own figures (final value $370,722.96, return 270.72%, largest fall 55.36%) differ by −$321.78, attributed to whole-share sizing and residual cash (−$321.78). Reconciliation does not certify vendor data or future profitability.

THE METHOD

the 4 rules every run of this strategy shares
  1. 01 · SIGNAL

    Ranks reconstructed filing-date snapshots by distinct buyers in the last 14 days; at least two buyers, top five. Unknown plan status is included by the inherited metric convention.

  2. 02 · PARAMETERS

    {"top_n":5,"min_cluster_size":2,"require_net_positive":false,"net_period":"30d","ranking":"cluster"}

  3. 03 · PUBLIC AVAILABILITY

    Form 4 filing day, available at end of that day; execute next session open. Reconstructed aggregate windows use filing dates, never undisclosed transaction dates.

  4. 04 · OUR ENGINE

    Independent event selector feeds the shared-cash portfolio engine; 548 admitted histories, monthly last-session signals, next open, no terminal liquidation.

This is the rule set the run above executes. Every number on this page is produced by these 4 steps with no discretionary override; the variants below each change exactly one setting. Long-only equal-weight targets; whole split-adjusted shares; no leverage or stop-loss. Positions may remain through rebalances and overnight; residual capital stays as cash.

WIN RATE · HOW IT IS COUNTED

per sale vs per day with sales — they are not the same number
PER SALE51.1%225 W · 215 L · 0 flat of 440 sales
SALES PER DAY WITH SALES3.8440 sales over 116 trading days with at least one sale
COUNTING RULEflat sale = non-winEach sale counts once, including partial sales; a flat sale is not a win; purchases and open holdings are excluded.

Two ways to count a win, and they disagree. Per sale is the share of sales that closed with a positive net result — the 51.1% above; each sale counts once, including partial sales, and purchases and open holdings are excluded. Per day with sales is the share of trading days with at least one sale whose sales added up to a positive total: 59 of 116 such days, 50.9%. Profitable sale-days are different from daily portfolio returns, and overlapping positions and sale lots are not independent trials. Read this number next to profit factor and concentration, never alone.

VARIANT COMPARISON

the pinned default first, then one-setting alternatives · same window and basis as the headline
VARIANTWHAT IT CHANGESNET EQUITY GAINMAX FALLCOMPARED WITH THE DEFAULT
DefaultThe pinned rules unmodified.+$270,401−55.4%Pinned default, shown first. No recommendation.
Top N -2One pinned setting changed; every other rule unchanged.+$163,716−55.7%Return lower by 106.7 percentage points; maximum fall larger by 0.4 percentage points.
Top N +2One pinned setting changed; every other rule unchanged.+$324,038−50.8%Return higher by 53.6 percentage points; maximum fall smaller by 4.6 percentage points.
Minimum signal -25%One pinned setting changed; every other rule unchanged.+$243,729−54.4%Return lower by 26.7 percentage points; maximum fall smaller by 1.0 percentage points.
Minimum signal +25%One pinned setting changed; every other rule unchanged.+$29,025−56.9%Return lower by 241.4 percentage points; maximum fall larger by 1.6 percentage points.
Weekly cadenceWeekly review instead of monthly; every other rule unchanged.+$67,125−52.0%Return lower by 203.3 percentage points; maximum fall smaller by 3.3 percentage points.

Each alternative changes exactly one setting of the pinned rules and is run on the same window, prices, costs and starting capital as the headline. The figures are stated neutrally: no recommendation is made, even where an alternative did better in this sample.

TRADE LOG + FILL AUDIT

every fill drillable · select a row for the full audit

Times are modelled from the session calendar: signals at the close and fills at the next session's scheduled open. Fill prices use that session's opening price from the daily price bar, with configured costs. These are not recorded trade timestamps. Newest first.

EXECUTEDSIGNALSYMBOLSIDEPOSITIONQTYFILL PRICEHELDFEENET P&L
Aug 31, 2026 · 4:00 PM ET closeUMHBuyOpened4,841$16.400 sessions · opened today$39.70—
Aug 31, 2026 · 4:00 PM ET closeGWRSBuyOpened8,639$9.190 sessions · opened today$39.70—
Aug 31, 2026 · 4:00 PM ET closeDKLBuyOpened1,436$55.250 sessions · opened today$39.67—
Aug 31, 2026 · 4:00 PM ET closeBABABuyOpened707$112.180 sessions · opened today$39.65—
Aug 31, 2026 · 4:00 PM ET closeAMRCBuyOpened3,608$22.000 sessions · opened today$39.69—
Jul 31, 2026 · 4:00 PM ET closeVRASellClosed19,389$3.4422 sessions$33.35−$9,572.06
Jul 31, 2026 · 4:00 PM ET closeKMXSellClosed1,447$57.8922 sessions$41.88+$7,531.26
Jul 31, 2026 · 4:00 PM ET closeCLNESellClosed37,352$1.9422 sessions$36.23−$3,809.53
Jul 31, 2026 · 4:00 PM ET closeBZUNSellClosed26,830$3.1043 sessions$41.56+$11,942.73
Jul 31, 2026 · 4:00 PM ET closeADSKSellClosed380$239.6022 sessions$45.52+$14,964.48
Jun 30, 2026 · 4:00 PM ET closeVRABuyOpened19,389$3.930 sessions · opened today$38.10—
Jun 30, 2026 · 4:00 PM ET closeKMXBuyOpened1,447$52.630 sessions · opened today$38.08—
Jun 30, 2026 · 4:00 PM ET closeCLNEBuyOpened37,352$2.040 sessions · opened today$38.10—
Jun 30, 2026 · 4:00 PM ET closeADSKBuyOpened380$200.000 sessions · opened today$38.00—
Jun 30, 2026 · 4:00 PM ET closeSHAKSellClosed1,561$56.5821 sessions$44.16−$11,536.17
Jun 30, 2026 · 4:00 PM ET closeGWRSSellClosed13,343$7.2421 sessions$48.30−$3,300.52
Jun 30, 2026 · 4:00 PM ET closeBZUNSellReduced10,835$2.8421 sessions$15.39+$2,028.91
Jun 30, 2026 · 4:00 PM ET closeBSXSellClosed2,066$43.2121 sessions$44.64−$10,631.14
May 29, 2026 · 4:00 PM ET closeSHAKBuyOpened1,561$63.910 sessions · opened today$49.88—
May 29, 2026 · 4:00 PM ET closeGWRSBuyOpened13,343$7.480 sessions · opened today$49.90—
May 29, 2026 · 4:00 PM ET closeBZUNBuyOpened37,665$2.650 sessions · opened today$49.91—
May 29, 2026 · 4:00 PM ET closeBSXBuyOpened2,066$48.310 sessions · opened today$49.90—
May 29, 2026 · 4:00 PM ET closeWASHSellClosed6,752$32.2320 sessions$108.81+$6,199.99
May 29, 2026 · 4:00 PM ET closeCHTRSellClosed1,269$143.4020 sessions$90.99−$29,408.96
Apr 30, 2026 · 4:00 PM ET closeWASHBuyOpened6,752$31.280 sessions · opened today$105.60—

Fill audit — Aug 3, 2026 · 9:30 AM ET · Sell VRA · Closed · 19,389 shares at $3.44

rebalance v1-rebalance-118 · fill v1-fill-00885 · select any row above

SELECTIONSelected basket at 2026-07-31 close; target 0; exposure 0
EXECUTION RULEModelled execution time: Aug 3, 2026 · 9:30 AM ET, the scheduled session open. Price: the session's split-adjusted daily opening price with configured adverse slippage. Signal: Jul 31, 2026 · 4:00 PM ET close. No recorded execution timestamp.
TARGET VS ACHIEVED WEIGHTTarget 0%; achieved 0% at the rebalance open
EXACT CASH BEFORE / AFTER330348.83920385 before; 397013.65012385 after
AVERAGE COST3.93 average cost per split-adjusted share; entry fees allocated proportionally on sales
POSITION CHANGE AND AGE19389 to 0 shares; 22 elapsed trading sessions
FEE / NOTIONAL33.35 fee; 66698.16 notional
NET FROM THIS SALE-9572.06 realized net from this sale

Report details. Source files, calculation basis and limitations · served report fingerprint bd399d6b7a5c2b67… · original engine result bce24f3e06d25398….

Backtests describe historical results and do not predict future results. These DEVELOPMENT BACKTEST results are hypothetical, not actual trading, and do not promise similar future results.

This disclosure is published by Quantellect Technologies Inc. for quantellect.ai.

Simulated results

Backtests, paper trading, research portfolios, estimated returns from public disclosures, scenario analysis, and examples generated by automated systems are hypothetical. Any result claimed to be actual trading must be separately identified and substantiated as such.

A hypothetical result is a calculation based on a model and assumptions. It does not show that a real account placed the trades, obtained the assumed prices, paid the assumed costs, or earned the displayed return. No representation is made that a user will achieve similar profits or losses.

Our research engine

Quantellect uses an internally developed backtesting engine. A published result should identify the engine version and run identifier used for that result. Where a result on this site does not show that information, it is a summary presentation and carries additional uncertainty; treat it as an illustration of a research rule, not as a reproducible record.

Different engines and different configurations of the same engine can treat order timing, price matching, partial fills, account balances, margin, fees, and event sequencing differently. Agreement between two runs cannot establish that their common assumptions are correct.

Hindsight and selection

Strategies are often designed after examining historical data. Selecting instruments, signals, parameters, start dates, or examples after viewing outcomes can make results look more favorable than a strategy would have looked in advance.

Repeated experimentation increases the chance of finding apparent success by luck. Performance can change materially when tested on a different period, instrument universe, market regime, or dataset. A successful evaluation period does not eliminate these risks.

Data availability and revisions

A simulation may use data that was revised, corrected, or unavailable when a historical trade would have occurred. Reporting date, transaction date, filing acceptance time, public release time, provider availability, and Quantellect ingestion time are distinct.

For a strategy based on filings, estimates, or economic releases, the availability assumption is especially important. Corporate action adjustments, delisted securities, stale instruments, symbol changes, missing observations, and the treatment of failed companies can materially affect performance. A current database is not necessarily a reliable reconstruction of what was knowable in the past.

Execution and costs

Historical prices do not guarantee executable prices. A model may not fully reflect bid and ask spreads, queue position, routing, latency, slippage, transaction fees, commissions, exchange fees, market impact, price limits, trading halts, rejected orders, or limited available volume.

A bar can contain a high and a low without establishing the order in which they occurred. An assumed entry, stop, and target in the same bar can therefore depend on an artificial sequencing rule. Results also depend on whether a signal can trade on the same observation used to generate it.

Unless the accompanying assumptions expressly include them, do not assume results include taxes, financing, stock borrowing fees, locate availability, recall risk, data costs, platform costs, or the value of the time needed to operate a strategy.

Options, futures, leverage, and short selling

Options simulations depend on contract selection, quote quality, spreads, assignment and exercise assumptions, expiration treatment, and volatility inputs. A quoted midpoint or theoretical valuation is not proof that an order could be filled.

Futures results depend on contract selection, roll treatment, continuous contract adjustments, expiry, settlement, margin, funding, and trading session definitions. Synthetic continuous prices may not correspond to an instrument that could have been bought or sold.

Leverage, margin calls, gaps, and short positions can create losses beyond initially committed funds. Simulated accounts may fail to capture the practical constraints and financial pressure of such losses.

Performance statistics and comparisons

A return depends on starting capital, leverage, reinvestment, cash flows, fees, exposure, currency, and the measurement period. Annualizing a short period can exaggerate its apparent significance. Win rate alone does not describe the size of gains and losses. A favorable average can conceal large drawdowns, illiquidity, or a few exceptional observations.

A benchmark is useful only with a clear comparison basis, including dates, dividends, currency, costs, and exposure. A score, confidence value, or ranking is not a calibrated probability unless its methodology expressly states and supports that interpretation.

Public disclosure estimates

Returns attributed to politicians, insiders, institutions, or other reported investors may be estimates based on incomplete disclosures. Reported value ranges, unknown trade prices, delayed disclosure, omitted positions, transfers, amendments, and unreported costs can materially change the result.

A portfolio reconstructed from a filing is not the filer's complete account record. A displayed estimate is not an audited personal return, proof of current ownership, or evidence that the person caused a market movement.

What to look for with each result

Read a result with its strategy description and version, engine and run identifier, instrument universe, evaluation dates, data sources and availability assumptions, starting capital, sizing and leverage, execution rules, costs included and omitted, benchmark, and material limitations, wherever those are shown. If assumptions or source information are missing, the result has additional uncertainty.

A presentation that distinguishes the period used to develop the strategy from any separate evaluation period, and explains material selection, optimization, or data exclusions, is more informative than one that does not.

Changes and corrections

Research methods, data, and software can change. A result reproduced after a correction can differ from an earlier version. Refer to the publication date and run information where shown, and report suspected problems to [email protected].

Use these results to examine research hypotheses. They do not establish suitability, assure future performance, or replace independent evaluation and appropriate professional advice. Rights and obligations that cannot lawfully be excluded remain unaffected.