Trendcraft Weekly: 0 signal changes, week of Oct 26
Zero signal changes this week. Three of five markets are on going into next week.
| −2.6% Model, this week (hypothetical) | −3.8% Model, since Oct 19 (hypothetical) | 0 Signal changes |
New here? How the rules work: five markets, one 200-day rule, built in four steps.
What moved the board
Last week's test ran through the Fed meeting. The Fed held at 3.75% to 4% on Wednesday, two officials voted for a hike, and futures kept the odds of a December hike above 80%. But the 10-year fell 6 basis points to 4.93%, nowhere near 5.10%, while December crude held over $100. By that test, bonds are still betting the Fed won't need to go much further.
Two stories ran the week: the bill for AI spending, and a crypto exchange hack.
Alphabet fell nearly 13% Thursday, its worst day on record, after sales missed forecasts and investors questioned the return on its AI spending. Amazon kept its $220 billion spending plan for the year. Intel fell almost 29% on Friday after a weak outlook. The Nasdaq composite dropped 2.86% that day, its worst session since June. For the week the Nasdaq-100 fell 1.98% and the S&P 500 0.57%.
Bitcoin took the hardest hit, down 5.50% to $76,715. Binance, the biggest exchange, paused withdrawals Thursday after a breach estimated in the billions of dollars, and traders cited the hack and the tech selloff.
Gold fell for a second week. December gold settled at $3,884.90 an ounce, down 3.07%. Thursday's data ran hot: the economy grew at a 3.4% annual rate last quarter, and September's PCE inflation rose to 3.6% from a year earlier. Both argue for higher rates, and because gold pays no interest, higher rates make it more expensive to hold.
The tension to watch
The Fed and the bond market read the same economy two ways. Hot growth and 3.6% inflation are the case for a December hike. The selloff in AI stocks is the case against: investment tied to the AI build-out has helped carry the economy, so if those companies pull back, growth slows and the pressure to hike fades. Both can't be right. If the 10-year climbs back above 5% while oil holds over $100, the inflation side is winning. If the yield falls below 4.80% while the Nasdaq-100 keeps losing ground, bonds are calling the slowdown first.
What the rules did
No signal changes. No market crossed its 200-day average, so nothing went on or off and nothing traded. The week did narrow the margins. The Nasdaq-100 is on at step 4 but only 1.8% above its average, down from 4.2% a week ago. Bitcoin is on at step 3, 4.8% above, down from 10.4%. Oil is on at step 4, still the strongest trend at 36.2% above. Gold stays in cash, 13.8% below. The 10-year is in cash too, 0.8% below its average, closer than last week's 1.6%. A bad week alone doesn't move the board: a market goes to cash only on a close below its average, and its size is cut only when its daily swings grow well past what they were when it was sized.
The record
Nasdaq took the most from the model this week; oil pulled the other way. The model portfolio was −2.6% this week and is −3.8% since the first issue on Oct 19 (margin version); the cash version was −2.6% and −3.8%.
Hypothetical: the published targets priced at each close from Oct 19, after modeled trading costs (half the bid-ask spread plus commission on every change) and margin interest at 5.0% a year on borrowed dollars, before taxes. It is a model, not an account. Every signal change is dated in the issue that announced it, so the record can be checked against what was published at the time.
| Read this with the numbers. Hypothetical backtest, not actual trading: the same rules run over Jun 2007 to Oct 19, 2026 made 18.6% a year, with a worst drop of 24.7%. That splits into 12.5% a year for 2007-2016 and 24.9% a year from 2017, so the recent stretch ran about twice the earlier one. The rules were chosen on 2007-2016 data; the volatility cut was added in October 2026 after looking at the whole period, so it is not tested out of sample. Before each 2x fund existed, it is simulated from its underlying market. Figures are after modeled trading costs and margin interest, before taxes. The real-time model since Oct 19 is hypothetical too. Neither is an account, and neither guarantees future results. |
Real-time model by month (%)
| Year | Jan | Feb | Mar | Apr | May | Jun | Jul | Aug | Sep | Oct | Nov | Dec | Total |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2026 | −3.8 | −3.8* |
Hypothetical model, margin version, after modeled costs. * From the first issue, Oct 19.
Backtest returns by year (%)
| 2007 | 2008 | 2009 | 2010 | 2011 | 2012 | 2013 | 2014 | 2015 | 2016 |
|---|---|---|---|---|---|---|---|---|---|
| +48.6* | +20.5 | −1.5 | +20.8 | +2.6 | +3.9 | +16.6 | +11.4 | −8.7 | +14.7 |
| 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026 |
| +87.6 | −4.1 | +35.2 | +47.7 | +5.4 | −0.4 | +16.7 | +18.1 | +38.1 | +23.7† |
Hypothetical backtest, $100,000 at the 1.5x cap, after modeled costs. Blue is a gain, orange a loss. * 2007 starts in June. † 2026 runs to Oct 19, where the backtest stops and the real-time model takes over. Every month since 2007 is on the Track record page.
The worst drops
| # | Depth | High | Low | Months down | Months to recover | Back to the high |
|---|---|---|---|---|---|---|
| 1 | −20.4% | Jan 2015 | Aug 2015 | 7 | 10 | Jun 2016 |
| 2 | −19.1% | Sep 2012 | Jun 2013 | 9 | 6 | Dec 2013 |
| 3 | −17.1% | Apr 2011 | Jun 2011 | 2 | 14 | Aug 2012 |
| 4 | −16.3% | Apr 2021 | Feb 2023 | 22 | 10 | Dec 2023 |
| 5 | −15.1% | Jun 2008 | Oct 2008 | 4 | 2 | Dec 2008 |
Hypothetical backtest: the five deepest falls from a month-end high, how long the fall took and how long the recovery took. Month-end values, so a drop that recovers inside a month doesn't show here: on daily closes the worst drop was −24.7% (Feb 24, 2023). The last month-end is Oct 19, 2026.
Best and worst stretches
| Period | Best | Worst | Worst ended | Average | Median | Lost money |
|---|---|---|---|---|---|---|
| 3 months | +36.7% | −20.0% | Aug 2015 | +4.8% | +4.3% | 35% |
| 1 year | +94.1% | −18.0% | Jan 2016 | +19.2% | +16.6% | 20% |
| 3 years | +157.5% | −2.6% | Sep 2015 | +63.1% | +50.1% | 2% |
| 5 years | +367.7% | +14.3% | Apr 2016 | +125.9% | +114.4% | 0% |
| 10 years | +896.3% | +210.4% | Dec 2018 | +433.7% | +422.5% | 0% |
Hypothetical backtest: every rolling window since May 2007. "Lost money" is the share of windows that ended below where they started. Same month-end basis.
What drove the backtest's last 12 months
| Crude oil | +20.3 pts | ||
| Nasdaq-100 | +7.5 pts | ||
| Gold | −0.2 pts | ||
| Bitcoin | −1.9 pts | ||
| 10-yr Treasury | −4.1 pts | ||
| Cash interest | +0.8 pts | ||
| Margin interest | −1.1 pts | ||
| Trading costs | −1.5 pts |
Each market's contribution, Oct 17, 2025 to Oct 19, 2026, in points of return; costs and interest are their own rows, and the rows add to the backtest's +19.8% for those 12 months. Hypothetical backtest.
The week in signals
| Close of | What happened | Traded |
|---|---|---|
| All week | Nasdaq, oil, bitcoin held their steps; gold, the 10-year stayed in cash. | No trade |
Where the book stands
| Market | Step | Status |
|---|---|---|
| Nasdaq-100 | 4 of 4 | 1.8% above its average |
| Crude oil | 4 of 4 | 36.2% above its average |
| Bitcoin | 3 of 4 | 4.8% above its average, building |
| 10-yr Treasury | off | 0.8% below its average |
| Gold | off | 13.8% below its average |
Exact position sizes, entry and add levels, and same-day changes are in the daily edition.
Get the signals the evening they happen, free. The daily edition goes out after every close with the model portfolio (margin and cash versions), the signal board, and the price levels to watch. Turn it on in your account settings.
About this publication. Trendcraft is the same for every reader and is not personalized investment advice. The publisher does not manage, trade or access reader accounts, and trades any personal account holding the model's positions only after each issue is sent.
Risk. The model uses 2x leveraged ETFs and, in the margin version, borrowed money. Leveraged funds lose value in volatile, sideways markets, and a broker can sell positions without notice in a margin call. Losses can be large and fast. Model and hypothetical results are not actual trading and do not guarantee future results.
How this is made. Signal tables are generated by a fixed program from daily price data. Commentary is drafted with AI and reviewed and edited by the publisher.
