> ## Content Index
> Fetch the complete content index at: https://trendcraft.ghost.io/llms.txt
> Use this file to discover other available public pages before exploring further.

# Trendcraft Weekly: 1 signal change, week of Nov 2
- URL: https://trendcraft.ghost.io/trendcraft-weekly-1-signal-change-week-of-nov-2/
- Published: 2026-11-07T19:43:34.000Z
- Updated: 2026-11-07T19:43:34.000Z
- Author: Steve Dugger
- Tags: trend-letter, weekly

One signal change this week. Two of five markets are on going into next week.

| −8.0%Model, this week (hypothetical) | −11.5%Model, since Oct 19 (hypothetical) | 1Signal changes |
| ------------------------------------ | ---------------------------------------- | --------------- |

New here? [How the rules work](https://trendcraft.ghost.io/methodology/): five markets, one 200-day rule, built in four steps.

## What moved the board

Last week's test leaned toward the slowdown side without settling it: the 10-year yield fell 7 basis points, about half the drop that would have marked a clear call, and the Nasdaq-100 kept losing ground. December crude, which had to hold its gain for the inflation side to win, fell 13.23%.

One event ran the week: Tuesday's midterm elections, which gave Democrats control of both the House and the Senate.

Stocks took it on Thursday. The Nasdaq-100 fell 6.36%, a day it has about once a year and its largest drop since March 2020\. The S&P 500 fell 4.36%, its worst day since April 2025\. Chipmakers led as investors weighed what a Democratic Congress could mean for the AI build-out, including tighter rules. The VIX jumped 69.66% that day, a move it has about once every 18 years. For the week the Nasdaq-100 fell 4.91% and the S&P 500 2.68%.

Oil fell further. The oil fund fell 12.1%, a week it has about once a year. Traders tied the drop to the election, which raised hopes the US war with Iran would wind down. Gold went the other way, up 4.71%. Friday brought the counterweight: employers added 165,000 jobs in October, more than double forecasts, and unemployment slipped to 4.1%. Futures put the odds of a December hike above 75%.

## The tension to watch

The election and the jobs report pull rates in opposite directions. Stronger hiring and firmer wages are the case for a hike at the Fed's December 8-9 meeting. Against that, oil and the AI spending boom both lost ground: cheaper oil eases prices directly, and slower data-center building would cool investment that has helped carry growth. If the December 4 jobs report runs hot again and the 10-year yield rises 20 basis points from this week's close, the hike case is winning. If crude falls another 10% and the yield gives back 15 basis points before the Fed meets, bonds are betting the election did some of the Fed's work for it.

## What the rules did

The one signal change: the Nasdaq-100 went to cash from step 4 on Friday and ended the week 3.5% below its 200-day average. Oil stays on at step 4, its margin cut to 17.8% above its average from 36.2%. Bitcoin is on at step 3, 4.0% above, down from 4.8%. Gold (9.4% below) and the 10-year (1.0% below) stay in cash. 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 selloff pushed the Nasdaq-100 through that line; oil fell harder but stayed well above it.

## The record

Nasdaq took the most from the model this week. The model portfolio was **−8.0%** this week and is **−11.5%** since the first issue on Oct 19 (margin version); the cash version was −8.0% and −11.5%.

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. |
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

![Value of $100 since June 2007, log scale: hypothetical backtest to the first issue, then the real-time model](https://storage.ghost.io/c/1b/07/1b077080-9430-4e43-a2b8-0e811afe5aca/content/images/2026/11/2026-11-06-record-long.png)

Value of $100 since June 2007, log scale. Gray: hypothetical backtest to the first issue (Oct 19, 2026). Blue: the real-time model since, also hypothetical. Lower panel: drop from the previous high.

![Value of $100 over the last 12 months: hypothetical backtest, then the real-time model](https://storage.ghost.io/c/1b/07/1b077080-9430-4e43-a2b8-0e811afe5aca/content/images/2026/11/2026-11-06-record-year.png)

Last 12 months. Gray: hypothetical backtest to Oct 19\. Blue: the real-time model since.

### Real-time model by month (%)

| Year     | Jan | Feb | Mar | Apr | May | Jun | Jul | Aug | Sep | Oct  | Nov  | Dec | Total       |
| -------- | --- | --- | --- | --- | --- | --- | --- | --- | --- | ---- | ---- | --- | ----------- |
| **2026** |     |     |     |     |     |     |     |     |     | −3.8 | −8.0 |     | **−11.5\*** |

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](https://trendcraft.ghost.io/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    |
| --------- | ---------------------------------------------------------------- | --------- |
| Fri Nov 6 | Nasdaq went to cash from step 4.                                 | Trade Mon |
| All week  | Oil, bitcoin held their steps; gold, the 10-year stayed in cash. | No trade  |

## Where the book stands

| Market         | Step   | Status                           |
| -------------- | ------ | -------------------------------- |
| Crude oil      | 4 of 4 | 17.8% above its average          |
| Bitcoin        | 3 of 4 | 4.0% above its average, building |
| 10-yr Treasury | off    | 1.0% below its average           |
| Gold           | off    | 9.4% below its average           |
| Nasdaq-100     | off    | 3.5% 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 how far each market is from its next move. 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.