Equity · China · stocks · Monthly Free

Sentiment Beta in China

Academic paper

Sentiment Beta, and Asset Prices: Evidence from China

AuthorsFengjiao Lin; Zhigang Qiu

Institute

Renmin University of China
Renmin University of China - School of Finance
School of Finance, Renmin University of China

Paper linkhttps://papers.ssrn.com/sol3/papers.cfm?abstract_id=3941220

Strategy in a nutshell

The investment universe comprises China A-Share stocks. Sentiment beta is estimated through a time-series regression (section 2.2 of the reference paper) using the following explanatory variables:

Market factor

Size factor

Value factor

Momentum factor

CICSI sentiment index

For each stock and each month, sentiment beta is defined as the regression coefficient on the sentiment index. Regressions are run on a rolling 36-month window, requiring at least 24 valid observations.

Stocks are then ranked by their sentiment beta and sorted into quintiles. The strategy goes long the lowest-quintile stocks and short the highest-quintile stocks, forming a value-weighted portfolio. Portfolios are rebalanced monthly.

Economic rationale

Unlike developed Western markets, the Chinese stock market is heavily dominated by retail investors, who often trade on sentiment rather than fundamentals. This structural feature creates opportunities for sentiment-driven anomalies.

The CICSI sentiment index provides a systematic way to capture investor mood and its effect on stock returns. Stocks with low sentiment beta are less sensitive to swings in investor sentiment and are therefore more resilient, while high-sentiment-beta stocks are more exposed to irrational retail-driven overreaction.

By systematically going long low-sentiment-beta stocks and shorting high-sentiment-beta stocks, the strategy exploits these inefficiencies. Profitability arises because sentiment shocks distort prices in predictable ways, which can be harvested by disciplined, factor-aware investors.

Entry & exit

Entry

On each month, rank FXI, ASHR, EWH, SPY, BIL by 126-day return and equal-weight the strongest 1 name(s).

Exit

Sell any holding that falls out of the top 1 at the next rebalance and rotate into the new leaders.

Market data required

Needs at least 126 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

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

History needed

≥ 126 trading days per symbol (about 6 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 Sentiment Beta 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 · 42 lines

"""
Quant Buffet interactive lab — sentiment-beta-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']
LOOKBACK = 126
TOP_N = 1
INVERT = False  # True = short-term reversal (rank ascending)

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

    def on_day(engine: PortfolioEngine, dt: pd.Timestamp) -> None:
        row = rets.loc[dt]
        if row.isna().all():
            return
        key = (dt.year, dt.month)
        if state["last"] == key:
            return
        state["last"] = key
        ranked = row.dropna().sort_values(ascending=INVERT)
        picks = list(ranked.head(TOP_N).index)
        if not INVERT:
            picks = [s for s in picks if ranked[s] > 0] or picks[:1]
        w = {} if not picks else {s: 1.0 / len(picks) for s in picks}
        engine.set_target_weights(dt, w)

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

"""
Quant Buffet interactive lab — sentiment-beta-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']
LOOKBACK = 126
TOP_N = 1
INVERT = False  # True = short-term reversal (rank ascending)

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

def on_day(engine: PortfolioEngine, dt: pd.Timestamp) -> None:
        row = rets.loc[dt]
        if row.isna().all():
            return
        key = (dt.year, dt.month)
        if state["last"] == key:
            return
        state["last"] = key
        ranked = row.dropna().sort_values(ascending=INVERT)
        picks = list(ranked.head(TOP_N).index)
        if not INVERT:
            picks = [s for s in picks if ranked[s] > 0] or picks[:1]
        w = {} if not picks else {s: 1.0 / len(picks) for s in picks}
        engine.set_target_weights(dt, w)

ready = rets.dropna(how="all").index.min() if rets.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

6.52%

Sharpe

0.39

Max DD

-57.88%

Vol

23.22%

Sortino

0.61

Beta

0.64

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: Momentum rotationAssets: FXI, ASHR, EWH, SPY, BIL

# Generated from Quant Buffet → QuantConnect LEAN
# Strategy: Sentiment Beta in China
# Detected pattern: Momentum rotation
# 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: Hold top 1 by 126-day return; monthly.

    def Rebalance(self):
        scores = {}
        for symbol in self.symbols:
            hist = self.History(symbol, 126 + 5, Resolution.Daily)
            if hist.empty: continue
            close = hist["close"]
            if hasattr(close, "unstack"):
                close = close.unstack(level=0).iloc[:, 0]
            if len(close) < 126 + 1: continue
            scores[symbol] = float(close.iloc[-1] / close.iloc[-126 - 1] - 1)
        ranked = sorted(scores.items(), key=lambda kv: kv[1], reverse=True)[:1]
        for symbol in self.symbols:
            self.SetHoldings(symbol, 0)
        if ranked:
            w = 1.0 / len(ranked)
            for symbol, _ in ranked:
                self.SetHoldings(symbol, w)

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