股票 · 全球 · 期货，ETF · 每月 Free

基于机器学习的实证资产定价

登录后收藏

学术论文

基于机器学习的实证资产定价

作者Meb Faber

机构

Institut Mines-Télécom Business School
Cambria Investment Management

论文链接https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1585517

导读

投资标的：EWZ、FXI、EWT、EWY、EIDO、THD、EPHE、ECH、EPOL、EZA、ARGT、TUR。再平衡：每月。Universe: EWZ, FXI, EWT, EWY, EIDO, THD, EPHE, ECH, EPOL, EZA, ARGT, TUR. Parameters: rebalance=monthly.

策略概要

该策略投资于71个国家股票市场，用机器学习预测1985–2021年未来一个月超额收益。OLS、LASSO、RF、GBRT和神经网络等多种模型使用88个市场特征预测收益。每月排名并分成五组，等权做多预测最高市场、做空最低市场，每月再平衡。

经济逻辑

策略成功主要来自错定价而非风险。套利受限、中小/新兴市场流动性不足以及行为偏差形成可利用异象。组合多种机器学习模型可提高预测稳定性，并捕捉统计显著的异常收益。

入场与出场

入场

每月由 make_on_day 决定目标权重。当前宇宙：EWZ, FXI, EWT, EWY, EIDO, THD, EPHE, ECH, EPOL, EZA (+2 more)。请对照实验室代码中的 engine.set_target_weights。

出场

权重被设为空或该标的权重为 0 即视为出场。引擎按 5 bps 佣金 + 2 bps 滑点执行。

所需行情数据

需要 EWZ, FXI, EWT, EWY, EIDO, THD (+6 more) 至少 60 根复权收盘价，才能形成第一个有效信号。ETF 仅交易日有行情。实验室通过 backtest.data.load_daily_prices 读取 Yahoo Finance。

标的

EWZ, FXI, EWT, EWY, EIDO, THD, EPHE, ECH, EPOL, EZA, ARGT, TUR

频率

每月 · 日频复权收盘价；信号按月再平衡（用当月最后一个有效交易日）

所需历史

每个标的至少 60 根交易日 K 线（约 3 个交易月），外加数根缓冲才能发出第一个信号。

字段

复权收盘价（Adj Close / auto_adjust Close）
交易日日期索引

凭证

回测与实验室：无需密钥
实盘下单才需要券商 / 交易所 API

API 与数据源

Quant Buffet 数据 API

实验室用 load_daily_prices 拉取 ASSETS 的复权收盘价面板，磁盘缓存后回测可复现。

提供方: backtest.data.load_daily_prices
鉴权: 回测无需密钥
接口: load_daily_prices(ASSETS, start="2000-01-01")

API / docs → /zh/docs/data-api

Yahoo Finance（yfinance）

美股 / ETF 复权 OHLCV，免费研究接口，有速率限制。

提供方: yfinance → Yahoo Finance
鉴权: 公开历史无需密钥
接口: Ticker.history / yf.download(auto_adjust=True)

API / docs → github.com/ranaroussi/yfinance

Onsite backtest IDE

Quant Buffet 原生回测 IDE

Edit and run Quant Buffet Python for 基于机器学习的实证资产定价 in the browser. Results update live with equity, drawdown, and metrics charts. Allowed: backtest.data, backtest.engine, backtest.metrics, numpy, pandas. Define ASSETS and make_on_day(prices). Shortcut: Ctrl+Enter. API docs →

IDE · 43 lines

"""
Quant Buffet interactive lab — 基于机器学习的实证资产定价
Allowed: backtest.data / backtest.engine / backtest.metrics, numpy, pandas.
Required: a module-level ASSETS list, and def make_on_day(prices) returning (on_day, ready)
"""
from __future__ import annotations

import numpy as np
import pandas as pd

from backtest.data import load_daily_prices
from backtest.engine import EngineConfig, PortfolioEngine
from backtest.metrics import compute_metrics

ASSETS = ['EWZ', 'FXI', 'EWT', 'EWY', 'EIDO', 'THD', 'EPHE', 'ECH', 'EPOL', 'EZA', 'ARGT', 'TUR']
REBALANCE_ONCE = False

def make_on_day(prices: pd.DataFrame):
    cols = [c for c in ASSETS if c in prices.columns]
    state = {"last": None, "done": False}

    def on_day(engine: PortfolioEngine, dt: pd.Timestamp) -> None:
        available = [s for s in cols if pd.notna(prices.at[dt, s])]
        if not available:
            return
        if REBALANCE_ONCE:
            if state["done"]:
                return
            state["done"] = True
            engine.set_target_weights(dt, {s: 1.0 / len(available) for s in available})
            return
        key = (dt.year, dt.month)
        if state["last"] == key:
            return
        state["last"] = key
        engine.set_target_weights(dt, {s: 1.0 / len(available) for s in available})

    counts = prices[cols].notna().sum(axis=1)
    need = max(1, len(cols) // 2)
    eligible = counts[counts >= need]
    ready = eligible.index.min() if not eligible.empty else None
    return on_day, ready

"""
Quant Buffet interactive lab — 基于机器学习的实证资产定价
Allowed: backtest.data / backtest.engine / backtest.metrics, numpy, pandas.
Required: a module-level ASSETS list, and def make_on_day(prices) returning (on_day, ready)
"""
from __future__ import annotations

import numpy as np
import pandas as pd

from backtest.data import load_daily_prices
from backtest.engine import EngineConfig, PortfolioEngine
from backtest.metrics import compute_metrics

ASSETS = ['EWZ', 'FXI', 'EWT', 'EWY', 'EIDO', 'THD', 'EPHE', 'ECH', 'EPOL', 'EZA', 'ARGT', 'TUR']
REBALANCE_ONCE = False

def make_on_day(prices: pd.DataFrame):
    cols = [c for c in ASSETS if c in prices.columns]
    state = {"last": None, "done": False}

def on_day(engine: PortfolioEngine, dt: pd.Timestamp) -> None:
        available = [s for s in cols if pd.notna(prices.at[dt, s])]
        if not available:
            return
        if REBALANCE_ONCE:
            if state["done"]:
                return
            state["done"] = True
            engine.set_target_weights(dt, {s: 1.0 / len(available) for s in available})
            return
        key = (dt.year, dt.month)
        if state["last"] == key:
            return
        state["last"] = key
        engine.set_target_weights(dt, {s: 1.0 / len(available) for s in available})

counts = prices[cols].notna().sum(axis=1)
    need = max(1, len(cols) // 2)
    eligible = counts[counts >= need]
    ready = eligible.index.min() if not eligible.empty else None
    return on_day, ready

Quant Buffet syntax cheat sheet (copy / insert)

Paste these fragments into the editor. The sandbox rejects QuantConnect, os, and network libraries.

Required imports

Only these libraries are allowed in the sandbox.

from __future__ import annotations

import numpy as np
import pandas as pd

from backtest.data import load_daily_prices
from backtest.engine import EngineConfig, PortfolioEngine
from backtest.metrics import compute_metrics

ASSETS list (whitelisted ETFs)

Module-level list. Tickers must be in the Quant Buffet whitelist.

ASSETS = ["SPY", "QQQ", "TLT", "GLD", "BIL"]

make_on_day contract

Must return (on_day, ready). on_day calls engine.set_target_weights.

def make_on_day(prices: pd.DataFrame):
    cols = [c for c in ASSETS if c in prices.columns]
    sma = prices[cols].rolling(200, min_periods=200).mean()
    state = {"last": None}

    def on_day(engine: PortfolioEngine, dt: pd.Timestamp) -> None:
        if sma.loc[dt].isna().all():
            return
        key = (dt.year, dt.month)
        if state["last"] == key:
            return
        state["last"] = key
        long = [
            s for s in cols
            if pd.notna(prices.at[dt, s]) and pd.notna(sma.at[dt, s])
            and prices.at[dt, s] > sma.at[dt, s]
        ]
        weights = {} if not long else {s: 1.0 / len(long) for s in long}
        engine.set_target_weights(dt, weights)

    ready = sma.dropna(how="all").index.min() if sma.notna().any().any() else None
    return on_day, ready

Set target weights

Weights should sum to about 1.0. Empty dict = 100% cash.

engine.set_target_weights(dt, {"SPY": 0.60, "BIL": 0.40})

Live backtest performance

CAGR

4.87%

Sharpe

0.32

Max DD

-63.05%

Vol

25.08%

Sortino

0.48

Beta

1.06

Run the backtest to populate charts.

Order records

Run the backtest to load every order fill alongside performance.

Export to your platform

Transform Quant Buffet lab code (ASSETS + make_on_day / PortfolioEngine) into native classes for a third-party IDE — then copy and paste.

Target platform

Run in: QuantConnect Cloud or LEAN CLI · QCAlgorithm with Equity securities and monthly rebalance.

Detected pattern: Custom / hybridAssets: EWZ, FXI, EWT, EWY, EIDO, THD, EPHE, ECH, EPOL, EZA, ARGT, TUR

# Generated from Quant Buffet → QuantConnect LEAN
# Strategy: 基于机器学习的实证资产定价
# Detected pattern: Custom / hybrid
# Source uses Quant Buffet lab APIs (ASSETS + make_on_day / PortfolioEngine).
# Review fees, data, and risk before live trading — educational export only.

from AlgorithmImports import *


class QuantBuffetExport(QCAlgorithm):
    def Initialize(self):
        self.SetStartDate(2010, 1, 1)
        self.SetCash(100000)
        tickers = ["EWZ", "FXI", "EWT", "EWY", "EIDO", "THD", "EPHE", "ECH", "EPOL", "EZA", "ARGT", "TUR"]
        self.symbols = []
        for t in tickers:
            if "-" in t:  # crypto proxy e.g. BTC-USD
                self.symbols.append(self.AddCrypto(t.replace("-USD", ""), Resolution.Daily).Symbol)
            else:
                self.symbols.append(self.AddEquity(t, Resolution.Daily).Symbol)
        self.Schedule.On(
            self.DateRules.MonthStart(self.symbols[0]),
            self.TimeRules.AfterMarketOpen(self.symbols[0], 30),
            self.Rebalance,
        )
        # Logic: Custom Quant Buffet logic — adapt the signal block to match your lab on_day().

    def Rebalance(self):
        # Pattern: custom — Custom Quant Buffet logic — adapt the signal block to match your lab on_day().
        # Default: equal-weight. Port your make_on_day weights here via SetHoldings.
        w = 1.0 / len(self.symbols) if self.symbols else 0.0
        for symbol in self.symbols:
            self.SetHoldings(symbol, w)

导出代码使用目标平台的原生类与库。请在第三方 IDE 中安装依赖后运行；实盘前请自行验证。