Informes
Recientes
Informe Diario
2026-05-08
Informe de Trading
1. Contexto Macro
La situación internacional se caracteriza por una volatilidad moderada, con el VIX en 17.07 (-0.06%). Los rendimientos de los bonos del Tesoro estadounidense a 10 y 30 años se encuentran en 4.392 (+0.83%) y 4.969 (+0.53%), respectivamente. El Ãndice del dólar estadounidense (DXY) se encuentra en 97.925 (-0.33%). El precio del petróleo crudo WTI es de 94.89 (+0.08%) y el oro se encuentra en 4720.0 (+0.43%).
2. Corto Plazo
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| SPM.MI | 4.59 | 4.21 | ALCISTA | 66.1% | 4.40 | 5.17 | 3.0 |
| FRE.DE | 39.89 | 41.89 | BAJISTA | 79.6% | 38.55 | 42.89 | 2.2 |
| SCYR.MC | 4.87 | 4.58 | ALCISTA | 66.1% | 4.70 | 5.32 | 2.6 |
| FER.MC | 60.78 | 56.73 | ALCISTA | 59.6% | 58.87 | 66.86 | 3.2 |
| DGE.L | 1568.80 | 1459.25 | ALCISTA | 57.2% | 1491.44 | 1733.13 | 2.1 |
Justificación: Los modelos GBM, HMM y ML coinciden en la dirección alcista para SPM.MI, SCYR.MC y FER.MC, mientras que el modelo Kalman es neutral. Para FRE.DE, el modelo Kalman es bajista, mientras que los demás modelos son alcistas.
3. Medio Plazo
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| SNDK | 1339.96 | 1529.39 | ALCISTA | 57.5% | 1182.11 | 1624.11 | 1.8 |
| IQV | 178.64 | 193.32 | BAJISTA | 43.8% | 166.81 | 200.65 | 1.9 |
| SHELL.AS | 37.15 | 34.59 | ALCISTA | 46.2% | 35.88 | 41.00 | 3.0 |
| STX | 766.44 | 816.11 | ALCISTA | 44.7% | 706.77 | 840.94 | 1.2 |
| PRY.MI | 143.80 | 157.20 | ALCISTA | 32.4% | 133.73 | 163.90 | 2.0 |
Justificación: Los modelos GBM, HMM y ML coinciden en la dirección alcista para SNDK, STX y PRY.MI, mientras que el modelo Kalman es alcista para SHELL.AS.
4. Largo Plazo
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| MCHP | 101.58 | 108.12 | ALCISTA | 44.7% | 95.22 | 111.39 | 1.5 |
| GSK.L | 1875.00 | 1759.93 | ALCISTA | 46.2% | 1800.33 | 2047.60 | 2.3 |
| URW.PA | 104.35 | 100.25 | ALCISTA | 66.1% | 101.97 | 110.51 | 2.6 |
| SHEL.L | 3211.50 | 3019.10 | ALCISTA | 46.2% | 3101.00 | 3500.10 | 2.6 |
| ROK | 448.55 | 484.66 | ALCISTA | 34.7% | 420.34 | 502.72 | 1.9 |
Justificación: Los modelos GBM, HMM y ML coinciden en la dirección alcista para MCHP, GSK.L, URW.PA y ROK.
5. Criptomonedas
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| ICP-USD | 3.15 | 3.36 | NEUTRAL | 33.8% | 2.71 | 3.46 | 0.7 |
| LINK-USD | 9.92 | 10.09 | NEUTRAL | 33.8% | 9.34 | 10.17 | 0.4 |
| XMR-USD | 396.24 | 408.58 | NEUTRAL | 20.0% | 371.47 | 414.75 | 0.7 |
| ZEC-USD | 564.26 | 577.11 | NEUTRAL | 33.8% | 482.33 | 583.53 | 0.2 |
| ENS-USD | 6.56 | 6.63 | NEUTRAL | 33.8% | 6.13 | 6.67 | 0.3 |
Justificación: Los modelos GBM, HMM y ML coinciden en la dirección neutral para las criptomonedas.
6. Cartera Diversificada
| Ticker | Peso | Precio | Vol |
|---|---|---|---|
| SPM.MI | 9.2% | 4.59 | 33% |
| FRE.DE | 11.4% | 39.89 | 27% |
| SCYR.MC | 11.0% | 4.87 | 28% |
| SNDK | 3.3% | 1339.96 | 94% |
| IQV | 5.8% | 178.64 | 53% |
| SHELL.AS | 11.2% | 37.15 | 27% |
| MCHP | 6.1% | 101.58 | 50% |
| GSK.L | 9.6% | 1875.00 | 32% |
| URW.PA | 16.9% | 104.35 | 18% |
| ICP-USD | 2.8% | 3.15 | 110% |
| LINK-USD | 6.6% | 9.92 | 46% |
| XMR-USD | 6.1% | 396.24 | 50% |
Justificación: La cartera diversificada busca equilibrar el riesgo y el retorno, con una distribución de pesos que refleja la confianza en cada activo.
7. Alertas
- Eventos earnings/dividendos que impactan recomendaciones:
- AEP: DIVIDEND el 2026-05-08
- AAPL: DIVIDEND el 2026-05-11
- BRO: DIVIDEND el 2026-05-11
- CEG: EARNINGS el 2026-05-11
- AWK: DIVIDEND el 2026-05-12
- AMAT: EARNINGS el 2026-05-14
8. Backtesting
- Que paso con lo recomendado ayer:
- SAND.ST: FALLO | Entrada $400.8, Hoy $375.0, Ret real -6.437%, Ret pred +0.818%, Dir ALCISTA (conf 60.2%)
- SPM.MI: FALLO | Entrada $4.592, Hoy $4.313, Ret real -6.076%, Ret pred -8.373%, Dir ALCISTA (conf 66.1%)
- BPE.MI: FALLO | Entrada $13.138, Hoy $12.4, Ret real -5.617%, Ret pred -1.025%, Dir ALCISTA (conf 55.9%)
- REP.MC: FALLO | Entrada $22.91, Hoy $21.84, Ret real -4.670%, Ret pred -7.312%, Dir ALCISTA (conf 60.8%)
- BAS.DE: FALLO | Entrada $53.45, Hoy $51.3, Ret real -4.022%, Ret pred +2.190%, Dir ALCISTA (conf 55.6%)
- ACX.MC: FALLO | Entrada $15.08, Hoy $14.56, Ret real -3.448%, Ret pred +1.748%, Dir ALCISTA (conf 55.9%)
- PAH3.DE: FALLO | Entrada $30.77, Hoy $31.8, Ret real +3.347%, Ret pred +1.837%, Dir BAJISTA (conf 57.9%)
- ITRK.L: FALLO | Entrada $5046.0, Hoy $4883.0, Ret real -3.230%, Ret pred -4.474%, Dir ALCISTA (conf 57.1%)
9. Performance Modelos
| Modelo | Accuracy | Sesgo | MAE |
|---|---|---|---|
| gbm | 53% | -0.33% | 1.78% |
| hmm_signal | 52% | - | - |
| ml | 52% | 1.56% | 11.13% |
| ensemble | 51% | -0.56% | 2.76% |
| kalman | 51% | -1.02% | 2.02% |
| merton | 49% | -0.45% | 1.61% |
| kalman_signal | 41% | - | - |
Justificación: El modelo GBM tiene la mayor precisión, mientras que el modelo kalman_signal tiene la menor precisión.
10. Calibracion
| Bucket | n | Hit rate | Avg conf |
|---|---|---|---|
| 00-30% | 23025 | 51% | 16% |
| 30-50% | 6940 | 51% | 39% |
| 50-60% | 572 | 49% | 57% |
| 60-70% | 644 | 59% | 62% |
| 70-80% | 111 | 56% | 79% |
| 80+% | 9 | 33% | 83% |
Justificación: La calibración muestra que la confianza en las predicciones es alta para los buckets de 60-70% y 70-80%, pero baja para el bucket de 80+%.
11. Disclaimer
Este informe es solo para fines informativos y no debe ser considerado como asesoramiento de inversión. Los resultados pasados no garantizan resultados futuros. Es importante hacer su propia investigación y consultar con un asesor financiero antes de tomar cualquier decisión de inversión.
12. Metricas Profesionales
Risk-adjusted metrics computadas sobre las ultimas 2000 evaluaciones del ensemble en los ultimos 30 dias. Proxy de retornos: +1%/-1% por hit/miss (bet de tamano fijo). Anualizacion: 252.
| Metrica | Valor |
|---|---|
| Sharpe (anualizado) | 1.98 |
| Sortino (anualizado) | 2.97 |
| Calmar | 0.55 |
| Max Drawdown | -63.43% |
| Profit Factor | 1.28 |
| Win Rate (= Hit Rate global) | 56.20% |
| Expectancy por trade | 0.124% |
| N evaluaciones | 2000 |
Hit rate por bucket de confianza
| Bucket conf. | N | Hit rate |
|---|---|---|
| 00-30 | 518 | 62.9% |
| 30-50 | 1068 | 59.7% |
| 50-60 | 0 | N/A |
| 60-70 | 228 | 51.8% |
| 70-80 | 0 | N/A |
| 80-100 | 186 | 22.6% |
13. Calibracion (post-isotonic)
Isotonic (PAV) calibrator entrenado sobre 224 muestras historicas el 2026-05-08T00:30:00Z. Las NUEVAS predicciones del sistema ya entregan confidence calibrada (raw_confidence se conserva para auditoria). Tabla comparativa: mismas 5000 evaluaciones recientes, mostradas por bucket antes (raw) y despues (calibrado) del mapeo.
Tabla comparativa por bucket
| Bucket | N raw | Hit rate raw | N calibrado | Hit rate calibrado |
|---|---|---|---|---|
| 00-30 | 3711 | 49.9% | 0 | N/A |
| 30-50 | 1090 | 50.3% | 0 | N/A |
| 50-60 | 105 | 44.8% | 0 | N/A |
| 60-70 | 75 | 33.3% | 0 | N/A |
| 70-80 | 17 | 41.2% | 0 | N/A |
| 80-100 | 2 | 0.0% | 5000 | 49.6% |
Curva isotonic (knots)
| raw_conf | calibrated |
|---|---|
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 29.0 | 100.0% |
| 30.0 | 100.0% |
| 30.0 | 100.0% |
| 30.0 | 100.0% |
| 30.0 | 100.0% |
| 30.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 37.0 | 100.0% |
| 42.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 44.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 45.0 | 100.0% |
| 49.0 | 100.0% |
| 49.0 | 100.0% |
| 49.0 | 100.0% |
| 49.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 50.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 52.0 | 100.0% |
| 55.0 | 100.0% |
| 55.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 57.0 | 100.0% |
| 60.0 | 100.0% |
| 60.0 | 100.0% |
Criterio de exito (bucket 80+ >= 70% hit_rate): NO (hit rate calibrado = 49.6%, n=5000). Razon: el raw signal esta anti-calibrado (hit rate DECRECE con confidence en los datos historicos). PAV es monotona no decreciente, por lo que no puede restaurar magnitudes altas cuando el input no las soporta. Para elevar el bucket 80+ al 70% habria que corregir el generador de confianza (no el calibrador) o flippear el signo de la direccion en el master_agent.
Notas: trained on 224 (raw_conf, hit) pairs | DEGENERATE: PAV collapsed to 1 block (value=1.0000). Raw signal is anti-calibrated (hit rate does not increase with raw_conf). Calibrator returns overall mean for all inputs — the real expected hit rate.
14. Sizing y Riesgo
Pipeline profesional: Kelly fraccional (0.25) -> Vol-target (15% anual) -> Cap de correlacion (max 20%). Muestreadas las ultimas 8 predicciones con sizing calculado.
Resumen
- Kelly medio: 2.50% (cap 20%)
- Risk score medio: 81.7/100 (100 = mas seguro)
- Predicciones con Kelly = 0: 7/8
Distribucion de Kelly size
| Rango Kelly | N | % |
|---|---|---|
| 0% | 7 | 87.5% |
| 0-5% | 0 | 0.0% |
| 5-10% | 0 | 0.0% |
| 10-15% | 0 | 0.0% |
| 15-20% | 1 | 12.5% |
Top-5 riesgo mas elevado (risk_score bajo)
| Symbol | Asset | Direction | Conf | Kelly | Risk |
|---|---|---|---|---|---|
| EURUSD=X | EUR/USD | ALCISTA | 57 | 20.00% | 61.0 |
| USO | Oil (WTI) | NEUTRAL | 52 | 0.00% | 64.1 |
| BTC-USD | Bitcoin | ALCISTA | 57 | 0.00% | 82.6 |
| GLD | Gold | NEUTRAL | 50 | 0.00% | 85.1 |
| QQQ | NASDAQ 100 | BAJISTA | 29 | 0.00% | 88.6 |
Sin alertas de riesgo extremo (todos los risk_score >= 40).
Caveats: vol anualizada estimada desde ATR% (rough ~16x daily). Cap de correlacion actualmente usa matriz vacia (penalty=1) cuando el agente analiza un unico simbolo; el cap duro del 20% sigue aplicandose. Kelly full nunca se usa — siempre 1/4 Kelly.
15. Top Picks del dia
Seleccion diaria por horizonte. Criterio: maximo score combinado = master_score * conf_cal/100 * sign(direction) * (1 - risk/100). CORTO usa GBM/Kalman, MEDIO stacking ensemble, LARGO fundamental+macro. Ver /top-picks para histograma y equity.
| Horizonte | Asset | Ticker | Dir | Conf cal | Master | Kelly | Precio | Target | Rationale |
|---|---|---|---|---|---|---|---|---|---|
| CORTO (1-7d) | AAL.L | AAL.L | ALCISTA | 100.0% | 50.0 | 0.00% | 3827.5000 | 3904.0500 | GBM/Kalman ensemble: conf_raw=27.1% (cal=100.0%), dir=ALCISTA, vol_annual=47.0%, regime=BULL |
| MEDIO (1-3m) | A2A.MI | A2A.MI | ALCISTA | 100.0% | 50.0 | 0.00% | 2.3840 | 2.3875 | Stacking ensemble (ridge): pred_return=0.14%, conf_raw=52.3% (cal=100.0%), dir=ALCISTA |
| LARGO (6-12m) | A2A.MI | A2A.MI | ALCISTA | 100.0% | 50.0 | 0.00% | 2.3450 | 2.6968 | Fundamental=70/100 (ATRACTIVO) + Macro=54/100 (NEUTRO); blend=62.0 -> ALCISTA, cal_conf=100.0% |
Caveats: target_price es indicativo (derivado del modelo y horizonte), NO es un precio objetivo formal. El rationale combina senales cuantitativas; no es analisis fundamental humano. El equity por horizonte en /top-picks necesita varios dias de acumulacion antes de ser estadisticamente significativo.