book
Checkout our new book! Hands on AI Trading with Python, QuantConnect, and AWS Learn More arrow

Quiver Quantitative

CNBC Trading

Introduction

The CNBC Trading dataset by Quiver Quantitative tracks the recommendations made by media personalities on CNBC and their historical performance. The data covers over 1,500 US Equities, starts in December 2020, and is delivered on a daily frequency. This dataset covers recommendations made on Mad Money, Halftime Report, and Fast Money.

This dataset depends on the US Equity Security Master dataset because the US Equity Security Master dataset contains information on splits, dividends, and symbol changes.

For more information about the CNBC Trading dataset, including CLI commands and pricing, see the dataset listing.

About the Provider

Quiver Quantitative was founded by two college students in February 2020 with the goal of bridging the information gap between Wall Street and non-professional investors. Quiver allows retail investors to tap into the power of big data and have access to actionable, easy to interpret data that hasn’t already been dissected by Wall Street.

Getting Started

The following snippet demonstrates how to request data from the CNBC Trading dataset:

self.aapl = self.add_equity("AAPL", Resolution.DAILY).symbol
self.dataset_symbol = self.add_data(QuiverCNBCs, self.aapl).symbol

self._universe = self.add_universe(QuiverCNBCsUniverse, self.universe_selection)
_symbol = AddEquity("AAPL", Resolution.Daily).Symbol;
_datasetSymbol = AddData<QuiverCNBCs>(_symbol).Symbol;

_universe = AddUniverse<QuiverCNBCsUniverse>(UniverseSelection);

Data Summary

The following table describes the dataset properties:

PropertyValue
Start DateDecember 25, 2020
Asset Coverage1,515 US Equities
Data DensitySparse
ResolutionDaily
TimezoneUTC

Requesting Data

To add CNBC Trading data to your algorithm, call the AddDataadd_data method. Save a reference to the dataset Symbol so you can access the data later in your algorithm.

class QuiverCNBCDataAlgorithm(QCAlgorithm):
    def initialize(self) -> None:
        self.set_start_date(2019, 1, 1)
        self.set_end_date(2020, 6, 1)
        self.set_cash(100000)

        self.aapl = self.add_equity("AAPL", Resolution.DAILY).symbol
        self.dataset_symbol = self.add_data(QuiverCNBCs, self.aapl).symbol
public class QuiverCNBCDataAlgorithm: QCAlgorithm
{
    private Symbol _symbol, _datasetSymbol;

    public override void Initialize()
    {
        SetStartDate(2019, 1, 1);
        SetEndDate(2020, 6, 1);
        SetCash(100000);
        _symbol = AddEquity("AAPL", Resolution.Daily).Symbol;
        _datasetSymbol= AddData<QuiverCNBCs>(_symbol).Symbol;
    }
}

Accessing Data

To get the current CNBC Trading data, index the current Slice with the dataset Symbol. Slice objects deliver unique events to your algorithm as they happen, but the Slice may not contain data for your dataset at every time step. To avoid issues, check if the Slice contains the data you want before you index it.

def on_data(self, slice: Slice) -> None:
    if slice.contains_key(self.dataset_symbol):
        data_points = slice[self.dataset_symbol]
        for data_point in data_points:
            self.log(f"{self.dataset_symbol} direction at {slice.time}: {data_point.direction}")
public override void OnData(Slice slice)
{
    if (slice.ContainsKey(_datasetSymbol))
    {
        var dataPoints = slice[_datasetSymbol];
        foreach (var dataPoint in dataPoints)
        {
            Log($"{_datasetSymbol} direction at {slice.Time}: {dataPoint.Direction}");
        }
    }
}

To iterate through all of the dataset objects in the current Slice, call the Getget method.

def on_data(self, slice: Slice) -> None:
    for dataset_symbol, data_points in slice.get(QuiverCNBCs).items():
        for data_point in data_points:
            self.log(f"{dataset_symbol} direction at {slice.time}: {data_point.direction}")
public override void OnData(Slice slice)
{
    foreach (var kvp in slice.Get<QuiverCNBCs>())
    {
        var datasetSymbol = kvp.Key;
        var dataPoints = kvp.Value;
        foreach(var dataPoint in dataPoints)
        {
            Log($"{datasetSymbol} direction at {slice.Time}: {dataPoint.Direction}");
        }
    }
}

Historical Data

To get historical CNBC Trading data, call the Historyhistory method with the dataset Symbol. If there is no data in the period you request, the history result is empty.

# DataFrame
history_df = self.history(self.dataset_symbol, 100, Resolution.DAILY)

# Dataset objects
history_bars = self.history[QuiverCNBCs](self.dataset_symbol, 100, Resolution.DAILY)
var history = History<QuiverCNBCs>(_datasetSymbol, 100, Resolution.Daily);

For more information about historical data, see History Requests.

Universe Selection

To select a dynamic universe of US Equities based on CNBC Trading data, call the AddUniverseadd_universe method with the QuiverCNBCsUniverse class and a selection function.

def initialize(self):
    self._uinverse = self.add_universe(QuiverCNBCsUniverse, self.universe_selection)

def universe_selection(self, alt_coarse: List[QuiverCNBCsUniverse]) -> List[Symbol]:
    cnbc_data_by_symbol = {}

    for datum in alt_coarse:
        symbol = datum.symbol
        
        if symbol not in cnbc_data_by_symbol:
            cnbc_data_by_symbol[symbol] = []
        cnbc_data_by_symbol[symbol].append(datum)
    
    # define our selection criteria
    return [symbol for symbol, d in cnbc_data_by_symbol.items()
            if len([x for x in d if x.direction == OrderDirection.BUY]) >= 3]
private Universe _universe;
public override void Initialize()
{
    _universe = AddUniverse<QuiverCNBCsUniverse>(altCoarse =>
    {
        var cnbcDataBySymbol = new Dictionary<Symbol, List<QuiverCNBCsUniverse>>();

        foreach (var datum in altCoarse.OfType<QuiverCNBCsUniverse>())
        {
            var symbol = datum.Symbol;

            if (!cnbcDataBySymbol.ContainsKey(symbol))
            {
                cnbcDataBySymbol.Add(symbol, new List<QuiverCNBCsUniverse>());
            }
            cnbcDataBySymbol[symbol].Add(datum);
        }

        // define our selection criteria
        return from kvp in cnbcDataBySymbol
            where kvp.Value.Where(x => x.Direction == OrderDirection.Buy) >= 3
            select kvp.Key;
    });
}

Universe History

You can get historical universe data in an algorithm and in the Research Environment.

Historical Universe Data in Algorithms

To get historical universe data in an algorithm, call the Historyhistory method with the Universe object and the lookback period. If there is no data in the period you request, the history result is empty.

var universeHistory = History(universe, 30, Resolution.Daily);
foreach (var cnbcs in universeHistory)
{
    foreach (QuiverCNBCsUniverse cnbc in cnbcs)
    {
        Log($"{cnbc.Symbol} traders at {cnbc.EndTime}: {cnbc.Traders}");
    }
}
# DataFrame example where the columns are the QuiverCNBCsUniverse attributes: 
history_df = self.history(self._universe, 30, Resolution.DAILY, flatten=True)

# Series example where the values are lists of QuiverCNBCsUniverse objects: 
universe_history = self.history(self._universe, 30, Resolution.DAILY)
for (_, time), cbncs in universe_history.items():
    for cbnc in cbncs:
        self.log(f"{cbnc.symbol} traders at {cbnc.end_time}: {cbnc.traders}")

Historical Universe Data in Research

To get historical universe data in research, call the UniverseHistoryuniverse_history method with the Universe object, a start date, and an end date. This method returns the filtered universe. If there is no data in the period you request, the history result is empty.

var universeHistory = qb.UniverseHistory(universe, qb.Time.AddDays(-30), qb.Time);
foreach (var cnbcs in universeHistory)
{
    foreach (QuiverCNBCsUniverse cnbc in cnbcs)
    {
        Console.WriteLine($"{cnbc.Symbol} traders at {cnbc.EndTime}: {cnbc.Traders}");
    }
}
# DataFrame example where the columns are the QuiverCNBCsUniverse attributes: 
history_df = qb.universe_history(universe, qb.time-timedelta(30), qb.time, flatten=True)

# Series example where the values are lists of QuiverCNBCsUniverse objects: 
universe_history = qb.universe_history(universe, qb.time-timedelta(30), qb.time)
for (_, time), cbncs in universe_history.items():
    for cbnc in cbncs:
        print(f"{cbnc.symbol} traders at {cbnc.end_time}: {cbnc.traders}")

You can call the Historyhistory method in Research.

Remove Subscriptions

To remove a subscription, call the RemoveSecurityremove_security method.

self.remove_security(self.dataset_symbol)
RemoveSecurity(_datasetSymbol);

If you subscribe to CNBC Trading data for assets in a dynamic universe, remove the dataset subscription when the asset leaves your universe. To view a common design pattern, see Track Security Changes.

Example Applications

The Quiver Quantitative CNBC Trading dataset enables you to create strategies using the latest recommendations made by media personalities on CNBC. Examples include the following strategies:

  • Taking short positions in securities that were mentioned by Jim Cramer (CNBC commentator) in the last week
  • Trading securities that were most/least discussed across CNBC programs over the last year

Classic Algorithm Example

The following example algorithm buys Apple stock if the net recommendation of media personalities on CNBC for Apple is positive. Otherwise, it holds cash.

from AlgorithmImports import *
from QuantConnect.DataSource import *

class QuiverCNBCsAlgorithm(QCAlgorithm):

    def initialize(self) -> None:
        self.set_start_date(2021, 10, 1)   #Set Start Date
        self.set_end_date(2021, 10, 31)    #Set End Date
        self.aapl = self.add_equity("AAPL", Resolution.DAILY).symbol
        # Subscribe to CNBC data for AAPL to generate trade signal
        self.dataset_symbol = self.add_data(QuiverCNBCs, self.aapl).symbol

        # history request
        history = self.history(self.dataset_symbol, 10, Resolution.DAILY)
        self.debug(f"We got {len(history)} items from historical data request of {self.dataset_symbol}.")

    def on_data(self, slice: Slice) -> None:
        for cnbcs in slice.Get(QuiverCNBCs).values():
            # Using mean prediction from CNBC analysts to be the trade signal
            # If the average CNBC insight is upward movement, invest AAPL
            if np.mean([cnbc.direction for cnbc in cnbcs]) > 0:
                self.set_holdings(self.aapl, 1)
            else:
                self.set_holdings(self.aapl, 0)
public class QuiverCNBCsAlgorithm : QCAlgorithm
{
    private Symbol _symbol, _datasetSymbol;

    public override void Initialize()
    {
        SetStartDate(2021, 10, 1);  //Set Start Date
        SetEndDate(2021, 10, 31);    //Set End Date
        _symbol = AddEquity("AAPL").Symbol;
        // Subscribe to CNBC data for AAPL to generate trade signal
        _datasetSymbol = AddData<QuiverCNBCs>(_symbol).Symbol;

        // history request
        var history = History<QuiverCNBCs>(new[] {_datasetSymbol}, 10, Resolution.Daily);
        Debug($"We got {history.Count()} items from historical data request of {_datasetSymbol}.");
    }

    public override void OnData(Slice slice)
    {
        foreach (var kvp in slice.Get<QuiverCNBCs>())
        {
            // Using mean prediction from CNBC analysts to be the trade signal
            // If the average CNBC insight is upward movement, invest AAPL
            if (kvp.Value.Average(x => (int) (x as QuiverCNBC).Direction) > 0)
            {
                SetHoldings(_symbol, 1);
            }
            else
            {
                SetHoldings(_symbol, 0);
            }
        }
    }
}

Framework Algorithm Example

The following example algorithm creates a dynamic universe of US Equities that have at least 3 positive opinions from CNBC sources. Each day, it then forms a equal-weighted portfolio with all the securities in the universe.

from AlgorithmImports import *
from QuantConnect.DataSource import *

class QuiverCNBCsDataAlgorithm(QCAlgorithm):

    def initialize(self) -> None:
        self.set_start_date(2021, 1, 1)
        self.set_end_date(2021, 6, 1)
        self.set_cash(100000)

        self.dataset_symbol_by_symbol = {}
        # Filter universe based on CNBC data
        self.add_universe(QuiverCNBCsUniverse, self.universe_selection)

        self.add_alpha(ConstantAlphaModel(InsightType.PRICE, InsightDirection.UP, timedelta(1)))

        # Invest equally to evenly dissipate the capital concentration risk
        self.set_portfolio_construction(EqualWeightingPortfolioConstructionModel())

    def universe_selection(self, data: List[QuiverCNBCsUniverse]) -> List[Symbol]:
        cnbc_data_by_symbol = {}

        for datum in data:
            symbol = datum.symbol
            
            if symbol not in cnbc_data_by_symbol:
                cnbc_data_by_symbol[symbol] = []
            cnbc_data_by_symbol[symbol].append(datum)
    
        # Select the stocks with at least 3 CNBC analysts to suggest buy, reassuring the signal
        return [symbol for symbol, d in cnbc_data_by_symbol.items()
                if len([x for x in d if x.direction == OrderDirection.BUY]) >= 3]

    def on_securities_changed(self, changes: SecurityChanges) -> None:
        for security in changes.added_securities:
            # Requesting CNBC Data
            symbol = security.symbol
            dataset_symbol = self.add_data(QuiverCNBCs, symbol).symbol
            self.dataset_symbol_by_symbol[symbol] = dataset_symbol
            
            # Historical Data
            history = self.history(dataset_symbol, 10, Resolution.DAILY)
            self.debug(f"We got {len(history)} items from our history request on {dataset_symbol}.")

        for security in changes.removed_securities:
            dataset_symbol = self.dataset_symbol_by_symbol.pop(security.symbol, None)
            if dataset_symbol:
                # Remove subscription of CNBC data to release computation resources
                self.remove_security(dataset_symbol)
public class QuiverCNBCsDataAlgorithm : QCAlgorithm
{
    private Dictionary<Symbol, Symbol> _datasetSymbolBySymbol = new();
    public override void Initialize()
    {
        SetStartDate(2021, 1, 1);
        SetEndDate(2021, 6, 1);
        SetCash(100000);

        // Filter universe based on CNBC data
        AddUniverse<QuiverCNBCsUniverse>(data =>
        {
            var cnbcDataBySymbol = new Dictionary<Symbol, List<QuiverCNBCsUniverse>>();

            foreach (var datum in data.OfType<QuiverCNBCsUniverse>())
            {
                var symbol = datum.Symbol;

                if (!cnbcDataBySymbol.ContainsKey(symbol))
                {
                    cnbcDataBySymbol.Add(symbol, new List<QuiverCNBCsUniverse>());
                }
                cnbcDataBySymbol[symbol].Add(datum);
            }

            // Select the stocks with at least 3 CNBC analysts to suggest buy, reassuring the signal
            return from kvp in cnbcDataBySymbol
                where kvp.Value.Where(x => x.Direction == OrderDirection.Buy).Count() >= 3
                select kvp.Key;
        });

        AddAlpha(new ConstantAlphaModel(InsightType.Price, InsightDirection.Up, TimeSpan.FromDays(1)));

        // Invest equally to evenly dissipate the capital concentration risk
        SetPortfolioConstruction(new EqualWeightingPortfolioConstructionModel());
    }

    public override void OnSecuritiesChanged(SecurityChanges changes)
    {
        foreach (var security in changes.AddedSecurities)
        {
            // Requesting CNBC Data
            var symbol = security.Symbol;
            var datasetSymbol = AddData<QuiverCNBCs>(symbol).Symbol;
            _datasetSymbolBySymbol.Add(symbol, datasetSymbol);

            // History request
            var history = History<QuiverCNBCs>(datasetSymbol, 10, Resolution.Daily);
            Debug($"We get {history.Count()} items in historical data of {datasetSymbol}");
        }
        
        foreach (var security in changes.RemovedSecurities)
        {
            var symbol = security.Symbol;
            if (_datasetSymbolBySymbol.ContainsKey(symbol))
            {
                // Remove subscription of CNBC data to release computation resources
                _datasetSymbolBySymbol.Remove(symbol, out var datasetSymbol);
                RemoveSecurity(datasetSymbol);
            }
        }
    }
}

Research Example

The following example lists US Equities mentioned by Jim Cramer.

#r "../QuantConnect.DataSource.QuiverCNBC.dll"
using QuantConnect.DataSource;

var qb = new QuantBook();

// Requesting data
var aapl = qb.AddEquity("AAPL", Resolution.Daily).Symbol;
var symbol = qb.AddData<QuiverCNBCs>(aapl).Symbol;

// Historical data
var history = qb.History<QuiverCNBCs>(symbol, 60, Resolution.Daily);
foreach (var cnbcs in history)
{
    foreach (QuiverCNBC cnbc in cnbcs)
    {
        Console.WriteLine($"{cnbc.Symbol} traders at {cnbc.EndTime}: {cnbc.Traders}");
    }
}

// Add Universe Selection
IEnumerable<Symbol> UniverseSelection(IEnumerable<BaseData> altCoarse)
{
    return from d in altCoarse.OfType<QuiverCNBCsUniverse>()
        where d.Traders.Contains("Cramer") select d.Symbol;
}
var universe = qb.AddUniverse<QuiverCNBCsUniverse<(UniverseSelection);

// Historical Universe data
var universeHistory = qb.UniverseHistory(universe, qb.Time.AddDays(-60), qb.Time);
foreach (var cnbcs in universeHistory)
{
    foreach (QuiverCNBCsUniverse cnbc in cnbcs)
    {
        Console.WriteLine($"{cnbc.Symbol} traders at {cnbc.EndTime}: {cnbc.Traders}");
    }
}
qb = QuantBook()

# Requesting Data
aapl = qb.add_equity("AAPL", Resolution.DAILY).symbol
symbol = qb.add_data(QuiverCNBCs, aapl).symbol

# Historical data
history = qb.history(QuiverCNBCs, symbol, 60, Resolution.DAILY)
for (symbol, time), cbncs in history.items():
    for cbnc in cbncs:
        print(f"{cbnc.symbol} traders at {cbnc.end_time}: {cbnc.traders}")

# Add Universe Selection
def universe_selection(alt_coarse: List[QuiverCNBCsUniverse]) -> List[Symbol]:
    return [d.symbol for d in alt_coarse if 'Cramer' in d.traders]

universe = qb.add_universe(QuiverCNBCsUniverse, universe_selection)
        
# Historical Universe data
universe_history = qb.universe_history(universe, qb.time-timedelta(60), qb.time)
for (_, time), cbncs in universe_history.items():
    for cbnc in cbncs:
        print(f"{cbnc.symbol} traders at {cbnc.end_time}: {cbnc.traders}")

Data Point Attributes

The Quiver Quantitative CNBC Trading dataset provides QuiverCNBCs, QuiverCNBC, and QuiverCNBCsUniverse objects.

QuiverCNBCs

QuiverCNBCs objects have the following attributes:

QuiverCNBC

QuiverCNBC objects have the following attributes:

QuiverCNBCsUniverse

QuiverCNBCsUniverse objects have the following attributes:

You can also see our Videos. You can also get in touch with us via Discord.

Did you find this page helpful?

Contribute to the documentation: