Subject: Re: Chart: timing with Nas100 RS screen
here is latest data from the data I have after follow-up with chatgpt on various errors:
Strategy Offset CAGR Shrpe Beta UI MDD times drawdowns
-10% or more
max days ever to
recover #days to recover from MDD only
Momentum5_-1
Momentum5 -1 19.8% 0.712 0.811 26.951 -58.9% 36 651 651
Momentum5_+1
Momentum5 1 20.5% 0.731 0.824 22.246 -57.2% 34 1373 1373
NDX 7.5% 0.403 1.206 44.611 -82.9% 15 3292 3292
Overlap_entry
_exit_-5 27.8% 0.882 0.706 17.400 -62.8% 38 491 67
Overlap_entry
_exit_-4 24.9% 0.807 0.724 18.873 -59.4% 35 484 43
Overlap_entry
_exit_-3 19.8% 0.707 0.684 19.069 -54.3% 38 483 58
Overlap_entry
_exit_-2 25.9% 0.863 0.683 18.857 -45.4% 34 465 123
Overlap_entry
_exit_-1 25.9% 0.830 0.734 16.185 -58.6% 42 489 44
Overlap_entry
_exit_+1 21.5% 0.727 0.757 17.608 -48.8% 48 529 43
PHL180_5_-1 22.0% 0.815 0.722 19.235 -54.7% 38 1214 1214
PHL180_5_+1 20.1% 0.758 0.744 20.829 -51.7% 33 1403 1403
SPY 7.9% 0.491 1.000 16.215 -55.2% 8 1020 869
highest CAGR was to a) stay ouf the market on trade day if SPY<325day SMA, b) buy the overlaps only of the two possible 5 stock strategies (1 is 9 month momentum winners in the Nasdaq100, the other the highest 5 of the ratio price/(sum of 180 day high price and 180 day low price), c) trade on the last day of each month, d) don't enter any position on trade day if that particular stock's 5 day share volume (not dollar volume) is less than its 60 day share volume; e) during the month after purchase, exist any stock no longer meeting "d" criteria i.e. make sure daily, f) despite getting out of a stock, if on the list and meets buy criteria on the last day of the month for holding the next month, you re-buy even if you got out early.
This strategy recovered from its worst drawdown in only 44 trading days, and its worst-ever recovery period for any -10% or worse drawdown was much less than SPY or NDQ's.
However, I’ll quantify each volume-triggered early sale: what happened if sold at the trigger versus held to the normal next rebalance, then summarize win rate and whether a few names explain most of the benefit.
Thought for 2m 29s
Computed.
For Overlap + volume entry filter + mid-month exit, trade day -1:
Item Result
early-sale events 68
Measurable events 67
Unique stocks sold early 45
Beneficial exits 34
Harmful exits 33
Beneficial rate 50.7%
Median stock return after exit to next rebalance -0.03%
Average stock return after exit to next rebalance +0.99%
So the rule is not consistently predictive. It is basically a coin flip by count.
The portfolio improvement came from a few large helpful exits offsetting many small or harmful exits. Top positive contributors:
Stock Approx portfolio benefit
TSLA +10.8%
VRTX +8.3%
SHLDQ +6.5%
PTON +5.7%
ISRG +5.4%
Top 5 helpful stocks explained about 62.6% of all positive exit benefit.
Marginal effect of adding the mid-month exit on top of entry filter:
Metric Change
CAGR +0.26 pts
Sharpe +0.015
Beta -0.022
UI -0.87
MDD +1.26 pts better
MDD recovery 18 days faster
Longest ≥10% recovery 140 days worse
My read: the entry filter is cleaner than the mid-month exit. The mid-month exit helps some headline metrics slightly, but its edge is not broad; it depends on a small number of exits.