Informes
Recientes
Informe Diario
2026-05-12
Informe de Trading
1. Contexto Macro
La situación internacional se caracteriza por una mayor volatilidad en los mercados, con un VIX en 18.95 (+3.10%) y un rendimiento del Tesoro de EE. UU. a 10 años en 4.41 (+1.05%). El Ãndice de riesgo geopolÃtico se encuentra en 0.53/1.00, lo que sugiere un entorno de moderada incertidumbre. El sentimiento del mercado es neutral, con un score de +0.011 según FinBERT NLP.
2. Corto Plazo
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| PRY.MI | 154.20 | 167.19 | ALCISTA | 54.5% | 144.29 | 173.68 | 2.0 |
| SYK | 282.58 | 264.49 | BAJISTA | 58.7% | 271.66 | 309.71 | 2.5 |
| SAND.ST | 362.60 | 333.39 | ALCISTA | 44.2% | 343.76 | 406.41 | 2.3 |
| CBOE | 350.48 | 330.60 | ALCISTA | 57.7% | 334.05 | 380.29 | 1.8 |
| COP | 115.55 | 109.25 | BAJISTA | 56.8% | 110.58 | 125.01 | 1.9 |
Justificación: Los modelos GBM, Kalman, HMM y ML coinciden en la dirección alcista para PRY.MI y CBOE, mientras que para SYK y COP, los modelos apuntan a una dirección bajista. SAND.ST presenta una señal mixta, con el precio GBM/Kalman apuntando a un lado y el régimen/HMM/ML apuntando al otro.
3. Medio Plazo
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| GEN | 22.40 | 24.38 | ALCISTA | 56.8% | 20.66 | 25.38 | 1.7 |
| MU | 795.33 | 887.71 | ALCISTA | 54.0% | 701.75 | 933.90 | 1.5 |
| DELL | 247.04 | 269.47 | ALCISTA | 40.9% | 221.03 | 280.68 | 1.3 |
| COR | 259.70 | 244.72 | BAJISTA | 56.8% | 233.99 | 282.17 | 0.9 |
| CSGP | 32.92 | 31.18 | BAJISTA | 57.7% | 31.07 | 35.54 | 1.4 |
Justificación: Los modelos GBM, Kalman, HMM y ML coinciden en la dirección alcista para GEN, MU y DELL, mientras que para COR y CSGP, los modelos apuntan a una dirección bajista.
4. Largo Plazo
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| NG.L | 1273.50 | 1193.93 | ALCISTA | 44.2% | 1245.15 | 1392.86 | 4.2 |
| ANET | 136.43 | 127.57 | ALCISTA | 42.2% | 123.73 | 149.72 | 1.0 |
| IONQ | 56.89 | 63.66 | ALCISTA | 39.6% | 48.58 | 67.05 | 1.2 |
| EPAM | 97.35 | 91.96 | BAJISTA | 45.8% | 92.36 | 105.43 | 1.6 |
| EOG | 133.31 | 127.78 | BAJISTA | 56.8% | 127.82 | 141.60 | 1.5 |
Justificación: Los modelos GBM, Kalman, HMM y ML coinciden en la dirección alcista para NG.L, ANET y IONQ, mientras que para EPAM y EOG, los modelos apuntan a una dirección bajista.
5. Criptomonedas
| Ticker | Precio | Pred | Dir | Conf | SL | TP | R/R |
|---|---|---|---|---|---|---|---|
| KSM-USD | 5.75 | 6.07 | NEUTRAL | 19.8% | 5.26 | 6.23 | 1.0 |
| ENS-USD | 7.28 | 7.57 | NEUTRAL | 22.7% | 6.63 | 7.72 | 0.7 |
| EGLD-USD | 4.75 | 4.94 | NEUTRAL | 20.5% | 4.40 | 5.04 | 0.8 |
| LINK-USD | 10.51 | 10.83 | NEUTRAL | 22.7% | 9.84 | 10.99 | 0.7 |
| AAVE-USD | 100.15 | 103.15 | NEUTRAL | 21.2% | 92.75 | 104.65 | 0.6 |
Justificación: Los modelos GBM, Kalman, HMM y ML coinciden en la dirección neutral para las criptomonedas, con un sesgo hacia la alcista para KSM-USD y ENS-USD.
6. Cartera Diversificada
| Ticker | Peso | Precio | Dir | Conf |
|---|---|---|---|---|
| PRY.MI | 8.2% | 154.20 | ALCISTA | 54.5% |
| SYK | 13.6% | 282.58 | BAJISTA | 58.7% |
| SAND.ST | 10.1% | 362.60 | ALCISTA | 44.2% |
| GEN | 6.8% | 22.40 | ALCISTA | 56.8% |
| MU | 4.5% | 795.33 | ALCISTA | 54.0% |
| DELL | 5.0% | 247.04 | ALCISTA | 40.9% |
| NG.L | 23.6% | 1273.50 | ALCISTA | 44.2% |
| ANET | 5.6% | 136.43 | ALCISTA | 42.2% |
| IONQ | 3.6% | 56.89 | ALCISTA | 39.6% |
| KSM-USD | 6.1% | 5.75 | NEUTRAL | 19.8% |
| ENS-USD | 5.9% | 7.28 | NEUTRAL | 22.7% |
| EGLD-USD | 7.1% | 4.75 | NEUTRAL | 20.5% |
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:
- AWK: DIVIDEND el 2026-05-12
- AMAT: EARNINGS el 2026-05-14
- AMGN: DIVIDEND el 2026-05-15
- CCEP: DIVIDEND el 2026-05-15
- CEG: DIVIDEND el 2026-05-15
- CF: DIVIDEND el 2026-05-15
8. Backtesting
- Que paso con lo recomendado ayer:
- STX: ACERTO | Entrada $782.64, Hoy $834.01, Ret real +6.564%, Ret pred +3.245%, Dir ALCISTA (conf 63.6%)
- TSLA: ACERTO | Entrada $428.35, Hoy $445.0, Ret real +3.887%, Ret pred +0.990%, Dir ALCISTA (conf 55.7%)
- LUV: FALLO | Entrada $41.31, Hoy $39.99, Ret real -3.195%, Ret pred +0.512%, Dir ALCISTA (conf 59.2%)
- GEV: ACERTO | Entrada $1040.15, Hoy $1073.08, Ret real +3.166%, Ret pred -0.508%, Dir ALCISTA (conf 67.0%)
- DB1.DE: FALLO | Entrada $242.7, Hoy $250.0, Ret real +3.008%, Ret pred +3.970%, Dir BAJISTA (conf 59.2%)
- WKL.AS: ACERTO | Entrada $61.72, Hoy $59.94, Ret real -2.884%, Ret pred +1.272%, Dir BAJISTA (conf 59.1%)
- INTC: ACERTO | Entrada $126.0, Hoy $129.44, Ret real +2.730%, Ret pred +13.143%, Dir ALCISTA (conf 51.7%)
- KMB: ACERTO | Entrada $98.31, Hoy $95.75, Ret real -2.604%, Ret pred +0.887%, Dir BAJISTA (conf 66.9%)
9. Performance Modelos
| Modelo | Accuracy | MAE | Sesgo |
|---|---|---|---|
| gbm | 56% | 2.12 | 0.13 |
| hmm_signal | 54% | - | - |
| kalman | 53% | 2.28 | 0.01 |
| ml | 52% | 12.37 | 2.39 |
| merton | 50% | 1.93 | -0.00 |
| ensemble | 50% | 3.27 | -0.13 |
| kalman_signal | 48% | - | - |
Justificación: El modelo gbm presenta la mayor precisión, seguido de cerca por hmm_signal y kalman.
10. Calibracion
| Bucket | n | Hit rate | Avg conf |
|---|---|---|---|
| 00-30% | 25861 | 50% | 16% |
| 30-50% | 7629 | 50% | 38% |
| 50-60% | 903 | 45% | 57% |
| 60-70% | 554 | 49% | 63% |
| 70-80% | 228 | 50% | 78% |
| 80+% | 7 | 14% | 83% |
Justificación: La calibración de las predicciones muestra que el modelo tiene una tendencia a sobreestimar la confianza en los buckets de alta confianza.
11. Disclaimer
Este informe de trading es solo para fines informativos y no debe ser considerado como asesoramiento de inversión. Los resultados pasados no garantizan resultados futuros. Es importante realizar su propia investigación y considerar su propia situación financiera 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) | -9.21 |
| Sortino (anualizado) | -9.19 |
| Calmar | -0.72 |
| Max Drawdown | -100.00% |
| Profit Factor | 0.33 |
| Win Rate (= Hit Rate global) | 24.90% |
| Expectancy por trade | -0.502% |
| N evaluaciones | 2000 |
Hit rate por bucket de confianza
| Bucket conf. | N | Hit rate |
|---|---|---|
| 00-30 | 738 | 21.5% |
| 30-50 | 1002 | 26.6% |
| 50-60 | 32 | 53.1% |
| 60-70 | 219 | 22.8% |
| 70-80 | 3 | 100.0% |
| 80-100 | 6 | 33.3% |
13. Calibracion (post-isotonic)
Isotonic (PAV) calibrator entrenado sobre 256 muestras historicas el 2026-05-12T00:30:00Z. 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 | 3873 | 50.9% | 0 | N/A |
| 30-50 | 1005 | 49.5% | 0 | N/A |
| 50-60 | 67 | 58.2% | 0 | N/A |
| 60-70 | 34 | 73.5% | 0 | N/A |
| 70-80 | 21 | 42.9% | 0 | N/A |
| 80-100 | 0 | N/A | 5000 | 50.8% |
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% |
| 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% |
| 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% |
| 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% |
| 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% |
| 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% |
| 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% |
| 70.0 | 100.0% |
Criterio de exito (bucket 80+ >= 70% hit_rate): NO (hit rate calibrado = 50.8%, 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 256 (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: 3.34% (cap 20%)
- Risk score medio: 81.0/100 (100 = mas seguro)
- Predicciones con Kelly = 0: 6/8
Distribucion de Kelly size
| Rango Kelly | N | % |
|---|---|---|
| 0% | 6 | 75.0% |
| 0-5% | 0 | 0.0% |
| 5-10% | 1 | 12.5% |
| 10-15% | 0 | 0.0% |
| 15-20% | 1 | 12.5% |
Top-5 riesgo mas elevado (risk_score bajo)
| Symbol | Asset | Direction | Conf | Kelly | Risk |
|---|---|---|---|---|---|
| USO | Oil (WTI) | ALCISTA | 57 | 6.75% | 56.2 |
| EURUSD=X | EUR/USD | ALCISTA | 57 | 20.00% | 61.0 |
| BTC-USD | Bitcoin | NEUTRAL | 52 | 0.00% | 83.2 |
| GLD | Gold | NEUTRAL | 50 | 0.00% | 86.3 |
| QQQ | NASDAQ 100 | BAJISTA | 29 | 0.00% | 88.4 |
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) | AAPL | AAPL | ALCISTA | 100.0% | 50.0 | 0.00% | 292.6800 | 298.5336 | GBM/Kalman ensemble: conf_raw=39.9% (cal=100.0%), dir=ALCISTA, vol_annual=23.4%, regime=BULL |
| MEDIO (1-3m) | AAF.L | AAF.L | ALCISTA | 100.0% | 50.0 | 0.00% | 403.4660 | 405.8134 | Stacking ensemble (ridge): pred_return=0.58%, conf_raw=53.3% (cal=100.0%), dir=ALCISTA |
| LARGO (6-12m) | AAPL | AAPL | ALCISTA | 100.0% | 50.0 | 0.00% | 292.6800 | 336.5820 | Fundamental=65/100 (ATRACTIVO) + Macro=54/100 (NEUTRO); blend=59.5 -> 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.