The S&P 500 closes today flat, at 7,704.13; the biggest riser is MRNA, up 6.98%

Validated over 1082 out-of-sample sessions, walk-forward: each day is predicted training only on earlier ones, retraining every 21 sessions. It is right 59.89% of the time against 51.20% for the majority class (always calling the more frequent outcome). Brier 0.23429 against 0.24986 with no model.

Of the 139 variables computed (the index, the 500 stocks one by one, VIX, rates, gold, copper and the calendar) the model keeps the 120 most correlated with the target every 21 sessions, chosen using past data only. Today's are listed one by one in prediccion.json.

The ranking is recomputed every session, and this is what moved from one to the next. Next to each move is the factor that produced it: momentum changes every day, value whenever the price does, and quality and growth only when new accounts come in. Why the price moved is not in this data, so it is not told.

The biggest moves in the whole index: COHR climbs 66 places, from #305 to #239 (Momentum 6.8 → 7.2, Value 3.9 → 4.0) and HAL drops 67 places, from #229 to #296 (Momentum 6.6 → 6.0).

Source: rankings_diarios.json.gz · rank by multi-factor (the average of the four), across the 465 companies with all four computed · scores on the 0-10 scale used on company pages, where 5 is the index average. See all 500 scored →

The section above shows the ranking moving; almost always it is the price moving it. This is the other thing: a quarterly or annual report rewrites value, quality and growth at once, and those are audited accounts, not a quote. Here is the before and after, on the 0-10 scale used on company pages, where 5 is the index average.

Filing date on EDGAR, not the quarter end. Scores come from the rankings calendar: the same ones each company page publishes. No opinion on the results, only the measured effect.

The rare thing on a Form 4 is a purchase. The largest on September 22, 2026: Horizon Kinetics Asset Management Llc, 10% Owner at Texas Pacific Land, bought 1 shares at $361.36 (0.00 million dollars), code P, meaning on the open market and with their own money. see the Form 4 →

A buying campaign, not a trade. Berkshire Hathaway Inc, Buffett Warren E, 10% Owner at Lennar Corp /New/, has bought on 3 consecutive trading sessions, September 17, 2026 to September 21, 2026: 2,743,529 shares for 212.4 million dollars, and after the last one declares 23,719,109 shares held. see the latest Form 4 → Only two of the 12 runs of three or more consecutive sessions in the Form 4 filings downloaded between August 25, 2025 and September 23, 2026 moved more money. That someone buys says nothing about where the price goes: what is checkable is that they filed it with the SEC session after session.

1 purchase were filed that day across 1 company. Over the 38 days the file covers, August 17, 2026 to September 23, 2026, there are 191 purchases worth 1,673 million dollars across 60 companies, against 2010 sales: which is why a purchase gets told and a sale gets tabulated. The largest of the whole window was LEN, 103.04 million on September 18, 2026.

The biggest sale of the day tells you nothing. Hershey Trust Co Trustee In Trust For Milton Hershey School, of Hershey, sold 1.7 million dollars of stock and still holds 775,749 shares: that is 1.27% of the position, and the sale was scheduled months in advance under a 10b5-1 plan. That is tax plumbing, not a view on the company.

Of the 3 sales filed that day, 3 scheduled. The largest as a share of holding was scheduled, so today the list does not start with a discretionary decision.

Source: Form 4 filings with the SEC · alertas_insiders.json, session of September 23, 2026. Every name links to its filing on EDGAR: the claim and the proof on the same line. Every purchase of the last few months, company by company: which insiders are buying.

The context over those same 38 days: 2010 sales worth 21,673 million dollars (2 with no declared price, outside that total), of which 785 were discretionary, and of those 209 exceeded 25% of the seller's position. That is where to look.

Growth 100 falls short of the benchmark over 27 years: +894.1% against +1,371.7%. The weakest is Growth 100, with an alpha of -1.35%: negative, meaning what it earns does not pay for the market risk it takes to earn it. Publishing the figure that comes out worst is the only reason the others deserve any credit.

Source: carteras.json · index based at 100 on December 31, 1998. Walk-forward with point-in-time data: on each date scoring uses only prices up to that day and fundamentals already filed with the SEC. 332 rebalances through September 22, 2026.

Over the past month the value portfolio lost -5.99% while momentum gained +0.29%. Across that six-month window the benchmark rose 11.2%, so this is not the whole market moving: it is a rotation inside one.

The extreme of the series is March 2, 2000, 27 years ago, at +48.0 points. And what happened after each extreme? Counted, not assumed: of the 5 extremes in momentum's favor with enough data after them, in 2 the lead had flipped sign six months later; of the 5 extremes in value's favor, in 3. That is a count over 10 episodes, not a rule.

Computed from carteras.json · 332 monthly rebalances between February 2, 1999 and September 22, 2026 (27 years) · 326 overlapping windows of 6 rebalances · recent stretch: the last 24 rebalances, the shortest run that still holds 4 non-overlapping windows.

With the rank and the score they carry before reporting. Section 03 will publish the after once the document reaches EDGAR, which is zero to three days later: the press release does not move our scores, the filed accounts do.

Source: calendario_resultados.json · Nasdaq public earnings calendar. Earnings date announced by each company, not the SEC filing date, which is not published in advance. Scores from the September 24, 2026 ranking.

• What insiders did yesterday. Form 4 can be filed up to two business days after the trade, so the freshest data is always the day before last.
• Whether momentum keeps winning. 27 years and 332 rebalances are not enough to claim a factor mean-reverts. We can describe what happened, not what comes.
• What any company is worth. This report computes no price targets. No Monte Carlo, no DCF, no fair value. When you see one elsewhere, ask which cost of capital discounted it and who chose that number.
• Whether the S&P rises tomorrow. We measured it with the same model (139 variables) and the same walk-forward protocol, over 1,082 out-of-sample sessions: the model calls direction right 53.51% of the time and saying "up" every single day is right 53.70%. The gap is noise: there is no signal, so we don't sell one. Both figures are recomputed every edition.