On October 1, the model replaced 18 of its 30 positions. One month later, all six of the month’s top-performing stocks are new additions resulting from that very rebalancing. However, three of the six worst-performing stocks are as well. The Wikifolio ended October down 11.64 percent, its weakest month since its launch in March.

October was not a good month for tech stocks. Concerns about AI spending by the major cloud companies have resurfaced; the SOX semiconductor index lost 15.4 percent over the month, and the Nasdaq fell 5.3 percent. That was its weakest month since March 2025. Quarterly earnings reports came out last week. Seagate and Teradyne beat expectations but still saw their shares fall. On October 30, $INTC (-4,15 %) l issued a weak outlook for the fourth quarter and plummeted 28.6 percent in a single day. SanDisk $SNDK (-7,04 %) , Marvell $MRVL (-6,1 %) and $AMD (-8,7 %) also saw double-digit declines. In the meantime, on October 28, the Fed kept interest rates at 3.75 to 4.00 percent; two members would have preferred to raise them already.

For a portfolio that, after rebalancing, is invested nearly half in semiconductors and memory

, this was the worst possible month:

📊 Monthly performance: −11.64%

📊 Price as of October 30: €104.23

📊 Performance since inception (March 13): +4.2%

📊 Largest loss since inception: −18.6% (previously −14.6%)

📊 Next rebalancing: Early January 2027

Performance & Comparison 🚀

The Nasdaq fell, the broad indices held steady, and the DAX even gained ground. The model clearly lagged behind this time, falling more than twice as far behind as the Nasdaq.

Performance Comparison (September 30–October 30, 2026, end of day, all as euro-denominated ETFs):

Global Quant 6-Factor: −11.64%

NASDAQ 100: −5.27%

FTSE All-World: −0.52%

S&P 500: +0.25%

DAX: +2.43%

The Wikifolio is now 17.5% below its high of €126.30 on June 22.

Buys & Sales 💶

On October 1, the third rebalancing took place—the largest one yet. 18 stocks out, 18 in, 12 remained.

The model sold all nine banks: Bankinter $BKT (-0,66 %) , Swedbank $SWED A (+0,91 %) , UniCredit $UCG (-0,48 %) , CaixaBank $CABK (-0,18 %) , BBVA $BBVA (+0,21 %) , BPER $BPE (+0,8 %) , Monte dei Paschi $BMPS (+0,58 %) , Banca Mediolanum $BMED (+0,64 %) and HSBC $HSBA (+0,45 %) . Also, Interactive Brokers $IBKR (-0,19 %) , Antofagasta $ANTO (-2,01 %) , Coeur Mining $CDE (-2,68 %) , AppLovin $APP (+3,73 %) , Airtel Africa $AAF (+0,58 %) , Merlin Properties $MRL (-0,34 %) , Solaria $SLR (-2,11 %) , Investor AB $INVE B (+0,21 %) and Pershing Square $PS (+3,45 %) . All were ranked below 40th place. You can see the returns on each position since the purchase on the slides.

It bought six healthcare stocks (Eli Lilly $LLY (+0,9 %) , Bristol-Myers Squibb $BMY (+1,4 %) , Vertex $VRTX (+0,05 %) , Incyte $INCY (-0,3 %) , Illumina $ILMN (-1,17 %) , WuXi AppTec $603259 ) and five semiconductor companies (Seagate $STX (-4,27 %) , Marvell $MRVL (-6,1 %) , Applied Materials $AMAT (-3,94 %) , Teradyne $TER (-7,04 %) , KLA $KLAC (-3,93 %) ). Also included is Fortinet $FTNT (-1,41 %) , CF Industries $CF (-0,33 %) , Marathon Petroleum $MPC (-0,05 %) , APA $APA (+1,04 %) , Pop Mart, the Hong Kong Stock Exchange $HKXCY , and Lion Finance $BGEO (+0 %) . Applied Materials and KLA had been sold by the model in July; now they’re back in the portfolio.

After the reshuffle, twelve of the thirty positions were semiconductor and memory stocks, accounting for a combined 44.8% of the portfolio.

Top Movers in October 🟢

The sectors that gained were those unrelated to AI. APA topped the list with +28.95%. The oil company reported preliminary third-quarter results on October 7 and repurchased 10.5 million of its own shares. Eli Lilly rose +24.24%. Third-quarter revenue rose 39 percent to $24.4 billion, driven by Mounjaro and Zepbound, and Lilly raised its full-year revenue forecast to $91 billion to $92 billion.

Marathon Petroleum gained +14.06%, even though the stock fell 7.4% on October 27 along with other refiners. CF Industries rose by +8.54%, Vertex by +8.41%, and Bristol-Myers Squibb by +1.54%. All six have been in the portfolio since October 1.

October’s Worst Performers 🔴

This list consists almost entirely of chip stocks. SanDisk saw the biggest loss at −32.92%; on October 30 alone, it fell by 13.5%. Teradyne dropped −30.60%. The earnings report on October 28 beat expectations, as did the outlook, yet the stock still fell. Seagate (−29.13%) saw the same pattern following its earnings report on October 27. Lam Research fell −26.19%, Marvell by −24.61%. Comfort Systems lost −24.43%. It’s not a chip stock, but the company manufactures climate control and electrical systems for data centers and is thus tied to the same sector. On October 23, following the quarterly earnings report—which did not include a 2027 outlook—the stock dropped about 8 percent in a single day.

Teradyne, Seagate, and Marvell were added to the portfolio on October 1. SanDisk, Lam Research, and Comfort Systems $FIX (-0,53 %) were already in the portfolio and were still among the gainers in September.

What’s in the portfolio now 🔍

Stock prices have fallen. The companies’ financial results look different so far. Key metrics for the 30 positions, each showing the median value as of October 31:

P/E ratio: 24.6

Revenue growth: +21.2%

Earnings per share growth: +48.8%

Net margin: 39.0%

Return on equity: 39.4%

Debt-to-equity ratio: 0.2

With a P/E ratio of 24.6, this portfolio isn’t exactly cheap. However, revenue is growing by one-fifth per year, and debt plays virtually no role. The next earnings season will show whether these figures hold up.

Conclusion 💡

October showed what a 44.8% gain means in this sector. When the sector turns, the entire portfolio turns with it. The pharmaceutical and oil stocks added during the rebalancing performed well, but they couldn’t keep up with the chip stocks. A few weeks ago, I calculated a sector limit. At 20 percent, it reduced the maximum drawdown by 2.1 points, but I haven’t implemented it yet. I don’t tinker with the rules in the middle of a drawdown.

What I want to look into is the timing. Rebalancing always takes place just before earnings season, and this time the earnings reports came out right in the first few weeks after the purchase. I’ll run the numbers to see if this is a real disadvantage or if it just happened to look that way this time before I make any changes.

❓ Question for the community

How did October go for you? Did you also have chips in your portfolio, and did you buy more, sell, or just sit it out?

👇 Share your thoughts in the comments!

➡️ Every month, you’ll find the complete Wikifolio update here—even in bad months—along with research from the model.

🗞️ Newsletter: codeandcapitalquant.beehiiv.com

📈 Wikifolio: https://www.wikifolio.com/de/de/w/wf0gquant6

In August, gold mines were the market's top performers. In September, they were the most expensive. Fresnillo
$FRES (-0,95 %) down 15 percent, Micron
$MU (-2,7 %) up 17. At the end of the month, the Wikifolio was up 1.03 percent, and one day later, I swapped out 18 of 30 positions.

September was all about interest rates and oil. Brent rose above $100 in the second week and, following a Saudi pipeline outage, briefly hit $110. U.S. inflation stood at 3.4 percent in August. On September 16, the Fed raised the benchmark interest rate by a quarter point to 3.75 to 4.00 percent, for the first time since July 2023. The 10-year U.S. yield subsequently climbed to 5.19 percent, a level last seen in 2007. This hardly bothered tech stocks. The Nasdaq hit a record high on September 21, and AMD has been worth one trillion dollars ever since. The situation was different in Europe. German inflation jumped to 3.3 percent, and the DAX lost about four percent over the month.

📊 Monthly performance: +1.03%

📊 Price as of September 30: €117.97

📊 Largest loss since inception: −14.6%

📊 Max performance: +18% (since March 13, 26)

Next rebalancing: Early January 2027

Performance & Comparison 🚀

The U.S. indices posted clear gains when calculated in euros, with the Nasdaq leading the way. The Wikifolio did not keep pace. It lagged behind the Nasdaq, S&P 500, and FTSE All-World, and outperformed only the DAX.

Performance Comparison (September 1–30, 2026, end of day):

Global Quant 6-Factor: +1.03%

NASDAQ 100: +4.18%

S&P 500: +2.90%

FTSE All-World: +1.95%

DAX: −4.07%

You can see what caused this in the two lists below. Tech stocks delivered, while mining stocks and a few individual stocks ate up a good chunk of those gains.

Purchases & Sales 💶

None in September itself. The model trades only on four dates per year, and the third was on October 1. What happened then is detailed in its own section below.

Top Movers in September 🟢

The month belonged to semiconductors and memory stocks. Midway through the month, Intel’s CEO said the company could currently only meet about half of the demand for processors. After that, the entire industry picked up steam. Micron
$MU (-2,7 %) topped the list with +16.91%, followed by SanDisk
$SNDK (-7,04 %) at +13.90% and TSMC
$2330 at +11.85%. Lam Research
$LRCX (-4,55 %) rose +11.12%, ASML
$ASML (-0,25 %) +10.06%. In between is Comfort Systems $FIX (-0,53 %) , a stock that has nothing to do with chips, up 10.47%. In August, Comfort Systems was still among the losers.

September’s Big Losers 🔴

Gold and silver declined in September, with silver falling much more sharply. Rising yields and a stronger dollar weighed on prices. Mining stocks followed suit. Fresnillo
$FRES (-0,95 %) lost −14.53%, Coeur Mining
$CDE (-2,68 %) −10.65%, and Endeavour Mining $EDV (-1,06 %) -7.50%. In August, all three were still on the other list with gains of over 25 percent. Merlin Properties fell −8.98%, Airtel Africa
$AAF (+0,58 %) down 7.76%, and Interactive Brokers
$IBKR (-0,19 %) fell by 6.79%.

Rebalancing on October 1 🔄

On October 1, the third rebalancing since the start took place. I swapped out 18 of 30 positions—more than ever before. In July, it was nine.

All nine banks are out: Bankinter
$BKT (-0,66 %) , CaixaBank
$CABK (-0,18 %) , BBVA
$BBVA (+0 %) , UniCredit
$UCG (-0,48 %) , BPER
$BPE (+0,8 %) , Monte dei Paschi $BMPS (+0,58 %) , Banca Mediolanum
$BMED (+0,64 %) , Swedbank$SWED A (+0,91 %) and HSBC
$HSBA (+0,45 %) . In addition, Interactive Brokers $IBKR (-0,19 %) , Antofagasta $ANTO (-2,01 %) , Coeur Mining
$CDE (-2,68 %) , AppLovin
$APP (+3,73 %) , Airtel Africa
$AAF (+0,58 %) , Merlin Properties and Solaria
$SLR (-2,11 %) . Investor AB
$INVE B (+0,21 %) and Pershing Square
$PSH (-0,21 %) are also no longer in the portfolio. So four of the six underperformers listed above are no longer in the portfolio.

Six stocks from the healthcare sector were added: Eli Lilly
$LLY (+0,9 %) , Bristol-Myers
Squibb
$BMY (+1,4 %) , Vertex $VRTX , Incyte
$INCY (-0,3 %) , Illumina
$ILMN (-1,17 %) and WuXi AppTec
$603259 . Five are from the semiconductor and storage sectors: Seagate
$STX (-4,27 %) , Marvell
$MRVL (-6,1 %) , Applied
Materials
$AMAT (-3,94 %), Teradyne
$TER (-7,04 %) and KLA
$KLAC (-3,93 %) . The rest is split among Fortinet
$FTNT (-1,41 %) , CF Industries
$CF (-0,33 %) , Marathon Petroleum
$MPC (-0,05 %) , APA
$APA (+1,04 %) , Pop Mart $9992 (-0,61 %) , Hong Kong Exchanges
$388 (-0,5 %) and Lion Finance
$BGEO (+0 %) .

Twelve remain: SanDisk, Micron, Western Digital, Nvidia, Lam Research, TSMC, ASML, Alphabet, Comfort Systems, Fresnillo, Endeavour and Newmont. All six of September’s top movers are included.

Two names stand out. Applied Materials and KLA I sold on July 1, up 92 and a gain of 90 percent. Now both are back in my portfolio. The model doesn’t remember what it has sold in the past. It only looks at where a stock stands in the ranking today.

Conclusion 💡

The portfolio looks different after October 1 than it did before. In September, about 41 percent was still in financial stocks; now there are two positions out of 30. Instead, 12 out of 30 are in semiconductors and memory, and six are in the healthcare sector. There’s no sector limit; the model sorts by score, not by industry. Trading won’t resume until early January.

How was your September? And did you hold onto your stocks after the pullback, or did you sell them? 👇

➡️ Every month, you’ll find the complete Wikifolio update here, along with research in between.

📈 Wikifolio $DE000LS9V052 (-0,58 %)

On July 1, the second rebalancing of my Wikifolio took place—a rule-based portfolio with 30 equally weighted positions that has been running since March 13. Nine positions out, nine in. I had expected this to shift the structure. When I checked the numbers, almost everything was the same as before.

A quick note on how it works

A Python scanner evaluates approximately 845 stocks from 14 indices daily based on six factors. Those that make it into the top 25 are purchased. Those that fall below rank 40 are removed. Quarterly adjustments, no sector allocation, no discretion.

What was dropped:

• 4 tech stocks: Applied Materials $AMAT (-3,94 %) (+92%), KLA-Tencor $KLAC (-3,93 %) (+90%), Broadcom $AVGO (-5,5 %) , Amphenol $APH (-2,72 %). Not because of earnings, but because the valuation could no longer keep up with the share price and the stock’s ranking plummeted.

• 5x Finance: ING $ING (+0 %), Jyske Bank $JYSK (+0,52 %), Unicaja $UNI (-0,06 %), Baader Bank $BWB (+0 %), Nu Holdings $NU (+9,37 %).

New additions:

• ASML $ASML (-0,25 %), Alphabet $GOOG (-1,57 %), SanDisk $SNDK (-7,04 %), Investor AB $INVE B (+0,21 %), BBVA $BBVA (+0,21 %), UniCredit $UCG (-0,48 %), Monte dei Paschi $BMPS (+0,58 %), Banca Mediolanum $BMED (+0,64 %), Swedbank $SWED A (+0,91 %).

The interesting part

Micron $MU (-2,7 %) stayed in the portfolio, up over 100 percent. The score held, and the ranking remained higher. A system that sells based on profit would have kicked Micron out first. The model treated these three big winners completely differently because it doesn’t know the purchase price at all.

And on the other hand:

SanDisk $SNDK (-7,04 %) was added that same evening, at 1,820 euros. The stock had already been on the buy list in April but wasn’t tradable at the time. Today, the position is down about 50 percent. The timing could hardly have been worse.

The sector breakdown before and after

Technology fell from 30 to 23.3 percent, financials rose from 36.7 to 40. Materials remained at 16.7.

A factor model does not distinguish between sectors. It sorts by score, and stocks in the same sector often receive similar scores because they are influenced by the same drivers. If one falls below rank 40, there is a high probability that another from the same sector is ready to take its place in the top 25. The model captures gains and returns to the same sector, just with different names.

My Conclusion

One quarter doesn’t prove anything. I don’t have a sector cap in the model because my backtest doesn’t have one either.

Next rebalancing: October 1.

Who among you uses a rule-based approach and has a sector cap in place?

I’m curious to know what percentage cap you use.