Equity · China · stocks · Weekly Free

Extrapolation in China

Academic paper

Extrapolation in China’s Stock Market: Returns, Price Crash Risk and Price Informativeness

AuthorsSiyuan Yang; Siyang Li

Institute

PBC School of Finance
Tsinghua University
PBCSF, Tsinghua University

Paper linkhttps://papers.ssrn.com/sol3/papers.cfm?abstract_id=3978914

Strategy in a nutshell

Universe: Chinese stocks in the CSMAR database with Eastmoney Guba (stock forum) sentiment data from CNRDS.

Sentiment measure: Expectation=Positive – Negative postsPositive + Negative posts\text{Expectation} = \frac{\text{Positive – Negative posts}}{\text{Positive + Negative posts}}Expectation=Positive + Negative postsPositive – Negative posts

Modeling:

Compute cross-sectional rank of sentiment expectations.

Estimate a non-linear regression with past 12 weekly returns (t to t–11).

Use rolling estimation periods (m–18 to m–7, m–22 to m–7, m–26 to m–7) and validation (m–6 to m–1).

Parameters are weighted averages across estimation windows, with weights = inverse MSFE (normalized).

Portfolio construction:

Portfolios are value-weighted, rebalanced weekly.

Each week, estimate predicted and residual expectations.

Double sort into terciles (30–40–30) by predicted & residual expectation → 9 portfolios.

Long: lowest predicted, highest residual.

Short: highest predicted, lowest residual.

Economic rationale

Investor Sentiment via Social Media: Builds on established evidence (e.g., StockTwits literature) that online sentiment is predictive of returns.

Decomposition of Expectations: Separating predicted vs. residual expectations reveals hidden information not captured by raw sentiment.

Robust Predictive Power: Both economic (portfolio performance) and statistical (regressions with controls) tests confirm significant return predictability.

Practical Strength: Strategy remains highly statistically significant even when value-weighted, important given China’s large number of microcaps.

Entry & exit

Entry

On each month, scan FXI, ASHR, EWH, SPY, BIL. Long every name whose close is above its 200-day SMA, equal-weight. Skip names still below the average. An empty weight dict is 100% cash.

Exit

At the next rebalance, drop any name whose close has fallen back to or below the 200-day SMA. If the whole book is below trend, go fully to cash. Fills use 5 bps commission and 2 bps slippage.

Market data required

Needs at least 200 adjusted daily closes on FXI, ASHR, EWH, SPY, BIL before the first signal is ready. ETF columns print on exchange sessions only. The lab loads Yahoo Finance via backtest.data.load_daily_prices.

Symbols

FXI, ASHR, EWH, SPY, BIL

Frequency

Weekly · Daily adjusted close; signals rebalance on the month change (last available session)

History needed

≥ 200 trading days per symbol (about 10 months), plus a few extra bars so the first signal can fire.

Fields

Adjusted close (Yahoo auto_adjust)
Session date index

Credentials

None for paper and the onsite lab
Broker or exchange API keys only for live orders

APIs & providers

Quant Buffet Data API

The lab calls load_daily_prices for the ASSETS panel of adjusted closes, then caches CSV so backtests replay the same series.

Provider: backtest.data.load_daily_prices
Auth: None for paper / sandbox backtests
Endpoints: load_daily_prices(ASSETS, start="2000-01-01")

API / docs → /en/docs/data-api

Yahoo Finance via yfinance

US equities and ETFs, adjusted OHLCV, free for research (rate limits apply).

Provider: yfinance → Yahoo Finance
Auth: None for public history
Endpoints: Ticker.history / yf.download(auto_adjust=True)

API / docs → github.com/ranaroussi/yfinance

Onsite backtest IDE

Quant Buffet native backtest IDE

Edit and run Quant Buffet Python for Extrapolation in China 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 · 40 lines

"""
Quant Buffet interactive lab — extrapolation-in-china
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 = ['FXI', 'ASHR', 'EWH', 'SPY', 'BIL']
SMA_DAYS = 200

def make_on_day(prices: pd.DataFrame):
    cols = [c for c in ASSETS if c in prices.columns]
    sma = prices[cols].rolling(SMA_DAYS, min_periods=SMA_DAYS).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]
        ]
        w = {} if not long else {s: 1.0 / len(long) for s in long}
        engine.set_target_weights(dt, w)

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

"""
Quant Buffet interactive lab — extrapolation-in-china
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 = ['FXI', 'ASHR', 'EWH', 'SPY', 'BIL']
SMA_DAYS = 200

def make_on_day(prices: pd.DataFrame):
    cols = [c for c in ASSETS if c in prices.columns]
    sma = prices[cols].rolling(SMA_DAYS, min_periods=SMA_DAYS).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]
        ]
        w = {} if not long else {s: 1.0 / len(long) for s in long}
        engine.set_target_weights(dt, w)

ready = sma.dropna(how="all").index.min() if sma.notna().any().any() 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

7.54%

Sharpe

0.58

Max DD

-29.87%

Vol

14.43%

Sortino

0.88

Beta

0.38

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: SMA trendAssets: FXI, ASHR, EWH, SPY, BIL

# Generated from Quant Buffet → QuantConnect LEAN
# Strategy: Extrapolation in China
# Detected pattern: SMA trend
# 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 = ["FXI", "ASHR", "EWH", "SPY", "BIL"]
        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: Long assets where close > SMA(200); equal-weight; monthly.

    def Rebalance(self):
        longs = []
        for symbol in self.symbols:
            hist = self.History(symbol, 200 + 5, Resolution.Daily)
            if hist.empty: continue
            close = hist["close"].unstack(level=0).iloc[:, 0] if hasattr(hist["close"], "unstack") else hist["close"]
            if len(close) < 200: continue
            if float(close.iloc[-1]) > float(close.iloc[-200:].mean()):
                longs.append(symbol)
        weight = 1.0 / len(longs) if longs else 0.0
        for symbol in self.symbols:
            self.SetHoldings(symbol, weight if symbol in longs else 0.0)

Exported code uses the platform’s native classes and libraries. Install dependencies in your third-party IDE, then run. Validate before live trading.