This is Quant500: we score S&P 500 companies every market day from public SEC data. Free, no account — today's ranking.
Correction: the 14 August 2026 report published a stale forecast
This is a forecast and it can be checked: tomorrow you will know whether we got it right. The model is right 60.04% of the time when it calls whether a day will be more turbulent than usual, against 51.09% for a coin flip, measured over 1051 sessions it never saw. Below, the running score and everything else.
01Today's call
Published before the open, checked at the close.
Historical frequency, not a forecast. We tried five different ways to predict direction and none of them work; the detail is in section 07.
Validated over 1051 out-of-sample sessions, walk-forward: each day is predicted training only on earlier ones. It is right 60.04% of the time against 51.09% for a coin flip. Brier 0.23466 against 0.24988 with no model.
How to read a 43.7%
A 43.7% does not mean "no". It means that in four of every ten days like today, the market moves more than usual. If tomorrow turns out turbulent, the model did not fail: the 43.7% happened.
A probabilistic forecast can only be judged over many days, like a weather forecaster. If they say 30% rain and it rains, they were not wrong; they would be wrong if it rained half the time they said 30%. That is why we publish the running score, and why it is worth more than any promise.
The 120 variables it looks at today
Of the 139 computed, the model keeps the 120 most correlated with the target each month, chosen using past data only. These are today's, grouped by source.
asim_21 asim_63 atr14 caida_max21 caida_max252 caida_max63 cierre_rango cierre_rango_5 curt_21 dist_ma10 dist_ma100 dist_ma20 dist_ma200 dist_ma5 dist_ma50 diurno diurno_10 ma20_50 ma50_200 ma5_20 nocturno nocturno_10 pend_ma10 pend_ma20 pend_ma5 pend_ma50 pos_rango21 pos_rango252 pos_rango63 racha rango_vs_atr ret_10d ret_1d ret_21d ret_2d ret_3d ret_5d ret_63d rsi_14 rsi_2 rsi_5 sube_min21 sube_min63 verdes_21 verdes_5 vol_10d vol_5d vol_63d vol_de_vol vol_r_21_63 vol_r_5_21 vol_rel20 vol_rel60 vol_tend vol_x_ret z_precio20 z_precio60ad ad_21 ad_5 asim_transv correlacion_implicita dispersion dispersion_5 dispersion_z equipond_menos_sp_21d equipond_menos_sp_5d max_21 max_252 max_63 max_menos_min_63 min_21 min_252 min_63 sobre_ma20 sobre_ma200 sobre_ma50dia_mes es_diciembre es_enero es_jue es_lun es_mar es_mie es_vie fin_mes ini_mes mes vencimientovix vix_5d vix_ma20 vix_pct252 vix_vs_vol vix_z63 vvix vvix_vs_vix vvix_z63curva curva_d5 irx_dif_5d tnx_d1 tnx_d21 tnx_d5 tnx_z63rut_1d rut_21d rut_5d rut_menos_sp21 rut_menos_sp5cobre_21d cobre_5d cobre_entre_oro_21d oro_5d oro_menos_sp_21dnas_menos_sp5 nasdaq_1d nasdaq_21d nasdaq_5dskew_idx_z6302Today's number
One figure, and what you need to read it properly.
The high of the past 23 months was +12.9 points, in the window ending June 16, 2026: four weeks later the gap is +1.1. At the other end of the same stretch, -8.5 on August 14, 2025.
Over the past month the value portfolio gained +3.54% while momentum lost -3.25%. Across that six-month window the benchmark rose 8.2%, so this is not the whole market moving: it is a rotation inside one.
Computed from carteras.json · 186 monthly rebalances between 2-Feb-2011 and 17-Jul-2026 (fifteen years) · 180 overlapping windows of 6 rebalances · recent stretch: the last 24 rebalances, the shortest run that still holds 4 non-overlapping windows.
03What the executives did
SEC Form 4, session of August 13, 2026. 4 sales, 6.9 million dollars.
The biggest sale of the day tells you nothing. Zaffino Peter, of American International Group, sold 2.8 million dollars of stock and still holds 556,004 shares: that is 6.21% 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 4 sales filed that day, 2 were discretionary and 2 scheduled. And here is the finding: the two largest sales as a share of holding were both discretionary.
| Company | Insider | % of holding | Value | Left |
|---|---|---|---|---|
| Merck & Co. Guindo Chirfi | EVP, Access, Policy & Comms | 21.4% | 1.35 M$ | 36,613 sh. |
| Amgen Khosla Rachna | SVP, Business Development | 16.4% | 0.52 M$ | 6,404 sh. |
| American International Group Zaffino Peter | Executive Chair | 6.2% | 2.80 M$ | 556,004 sh. |
| Snap-On Pagliari Aldo John | Sr VP - Finance & CFO | 4.4% | 2.24 M$ | 120,644 sh. |
| American International Group Zaffino Peter · largest of the day by dollar value | Executive Chair | 6.2% | 2.80 M$ | 556,004 sh. |
Source: Form 4 filings with the SEC · alertas_insiders.json, session of 13-Aug-2026.
The 90-day context: 466 sales worth 2,422 million dollars (1 with no declared price, outside that total), of which 219 were discretionary, and of those 70 exceeded 25% of the seller's position. That is where to look.
Before drawing conclusions
Executives sell for divorces, mortgages, taxes and school fees, not only because they see clouds. The SEC does not require a reason, and we do not know it.
What we do know is that these people chose the timing. It is a map of where to look. It is not a sell signal.
04The three portfolios that can actually be audited
Rebuilt month by month using only what was known on the day.
| Portfolio | Cumulative | CAGR | Sharpe | Max DD | This year | Last month |
|---|---|---|---|---|---|---|
| Value 100Earnings, book and sales yield | +618.1% | 13.53% | 0.57 | -50.58% | +17.53% | +3.54% |
| Momentum 10012m return ex-latest month / volatility | +657.6% | 13.92% | 0.75 | -35.76% | +21.19% | -3.25% |
| Quality 100Balance-sheet and earnings quality | +685.0% | 14.18% | 0.76 | -33.06% | +8.66% | +0.37% |
| Universe average synthetic benchmark, carries survivorship bias | +474.9% | — | — | — | — | — |
All three beat the benchmark (+474.9%) on cumulative return over fifteen years, but cumulative return is not the proof: the benchmark carries the bias explained below. The weakest is Value 100, with an alpha of -0.00%: essentially zero, meaning its gains are explained by market exposure rather than by the factor. Publishing the figure that comes out worst is the only reason the others deserve any credit.
That benchmark is not the S&P 500
The +474.9% in the row above is not an index you can buy: it is the equal-weighted average of the universe companies whose prices we still hold, so the ones that left the index dropped out along the way and the figure is inflated by survivorship bias.
Over this same window the two ETFs that actually trade returned +393.7% (RSP, the equal-weighted S&P 500) and +530.6% (SPY, the plain S&P 500). The synthetic benchmark runs 81.3 points ahead of RSP, its fair comparable because both weight equally: that distance is the measure of what the bias adds. Do not line them up against the rows above to decide who wins: the portfolios carry the same bias as the synthetic benchmark and the ETFs do not. The ETFs also have their management fee already deducted (0.20% RSP, 0.09% SPY) while the portfolios are measured with no costs, and that asymmetry also flatters the portfolios.
Source: carteras.json · index based at 100 on 2-Feb-2011. 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. 186 rebalances through 17-Jul-2026.
The site's other five portfolios are not here. They are not picked by factor ranking, so their history cannot be rebuilt without looking ahead: their figures are today's holdings applied to the past, which inflates them. Until they have a walk-forward test, they stay out of this report.
05Today's question
Is momentum's lead running out, or just catching its breath?
Source: carteras.json · index based at 100 on 2-Feb-2011. 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. 186 rebalances through 17-Jul-2026.
The three windows where momentum pulled furthest ahead of value are +28.0 (9-Jul-2020), +23.4 (8-May-2020), +19.1 (7-Aug-2020). The widest is July 9, 2020, six years ago: the extreme of the series is not a recent event, and the window closing July 17, 2026 is worth +1.1 points.
At the other end, the three where value led: -43.1 (10-May-2021), -35.5 (9-Apr-2021), -32.5 (10-Mar-2021); the widest, May 10, 2021, five years ago.
And after an extreme? Counted, not assumed: of the 4 extremes in momentum's favour with enough data after them, in 3 the lead had flipped sign six months later; of the 5 extremes in value's favour, in 3. That is a count over 9 episodes, not a rule.
Why this is not a forecast
180 overlapping windows are not 180 independent observations: each shares five of its six rebalances with the next. With that overlap, any series looks mean-reverting whether it is or not.
What this chart supports is descriptive: the gap between the two factors is +1.1 points today, and last month belonged to Value 100. What happens next month is not in this data.
06The close, in three figures
Context, not headline.
Closing levels of ^GSPC, ^VIX and ^TNX (Yahoo Finance) · session of 13-Aug-2026.
The S&P 500 rose 0.65% in the session of August 13, 2026 and the VIX closed at 14.63. None of that explains the factor rotation in section 02, which is why it sits in section six rather than section one.
07The limits, and what they teach
A fixed section. Knowing where a model stops is worth as much as knowing what it gets right.
- Why each executive sold. The SEC requires the filing, not the motive. Anyone who tells you the motive is making it up.
- 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 value keeps winning. Fifteen years and 186 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 139 variables over 1051 out-of-sample sessions: the model calls direction right 54.28% of the time and saying "up" every single day is right 54.12%. There is no signal, so we don't sell one.
Next: What the S&P 500 is · today's ranking · all the guides.
This is not investment advice. Quant500 publishes data and its historical reconstruction. No figure here is a suggestion to buy or sell, nor does it account for your personal situation.
Report generated automatically on August 14, 2026 from the server's data files. Each section states its own cut-off date, which is not always today.
📚 Historical Daily Market Reports Archive
Browse all previous opening and closing market report editions.