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

Tiingo

Tiingo News Feed

Introduction

The Tiingo News Feed dataset by Tiingo tracks US Equity news releases. The data covers 10,000 US Equities, starts in January 2014, and is delivered on a second frequency. This dataset is creating by Tiingo integrating over 120 different news providers into their platform.

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 Tiingo News Feed dataset, including CLI commands and pricing, see the dataset listing.

About the Provider

Tiingo was founded by Rishi Singh in 2014. Tiingo goes beyond traditional news sources and focuses on finding rich, quality content written by knowledgeable writers. Their proprietary algorithms scan unstructured, non-traditional news and other information sources while tagging companies, topics, and assets. This refined system is backed by over ten years of research and development, and is written by former institutional quant traders. Because of this dedicated approach, Tiingo's News API is a trusted tool used by quant funds, hedge funds, pension funds, social media companies, and tech companies around the world.

Getting Started

The following snippet demonstrates how to request data from the Tiingo News Feed dataset:

self.aapl = self.add_equity("AAPL", Resolution.MINUTE).symbol
self.dataset_symbol = self.add_data(TiingoNews, self.aapl).symbol
_aapl = AddEquity("AAPL", Resolution.Minute).Symbol;
_datasetSymbol = AddData<TiingoNews>(_aapl).Symbol;

Data Summary

The following table describes the dataset properties:

PropertyValue
Start DateJanuary 2014
Asset Coverage10,000 US Equities
Data DensitySparse
ResolutionSecond
TimezoneUTC

Requesting Data

To add Tiingo News Feed 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 TiingoNewsDataAlgorithm(QCAlgorithm):
    def initialize(self) -> None:
        self.set_start_date(2021, 1, 1)
        self.set_end_date(2021, 6, 1)
        self.set_cash(100000)

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

    public override void Initialize()
    {
        SetStartDate(2021, 1, 1);
        SetEndDate(2021, 6, 1);
        SetCash(100000);

        _symbol = AddEquity("AAPL", Resolution.Minute).Symbol;
        _datasetSymbol = AddData<TiingoNews>(_symbol).Symbol;
    }
}

Accessing Data

To get the current Tiingo News Feed 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):
        article = slice[self.dataset_symbol]
        self.log(f"{self.dataset_symbol} article description at {slice.time}: {article.description}")
public override void OnData(Slice slice)
{
    if (slice.ContainsKey(_datasetSymbol))
    {
        var article = slice[_datasetSymbol];
        Log($"{_datasetSymbol} article description at {slice.Time}: {article.Description}");
    }
}

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

def on_data(self, slice: Slice) -> None:
    for dataset_symbol, article in slice.get(TiingoNews).items():
        self.log(f"{dataset_symbol} article description at {slice.time}: {article.description}")
public override void OnData(Slice slice)
{
    foreach (var kvp in slice.Get<TiingoNews>())
    {
        var datasetSymbol = kvp.Key;
        var article = kvp.Value;
        Log($"{datasetSymbol} article description at {slice.Time}: {article.Description}");
    }
}

Historical Data

To get historical Tiingo News Feed 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
self.history[TiingoNews](self.dataset_symbol, 100, Resolution.DAILY)
var history = History<TiingoNews>(_datasetSymbol, 100, Resolution.Daily);

For more information about historical data, see History Requests.

Remove Subscriptions

To remove a subscription, call the RemoveSecurityremove_security method.

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

If you subscribe to Tiingo News Feed 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 Tiingo News Feed enables you to accurately design strategies harnessing news articles on the companies you're trading. Examples include the following strategies:

  • Creating a dictionary of sentiment scores for various words and assigning a sentiment score to the content of each news release
  • Calculating the sentiment of news releases with Natural Language Processing (NLP)
  • Trading securities when their news releases are tagged by Tiingo with current buzzwords
  • Detecting impactful news in ETF constituents

Classic Algorithm Example

The following example algorithm assigns a sentiment score to each news article that's released for Apple. When the sentiment score is positive, the algorithm buys Apple stock. When the sentiment score is negative, it short sells Apple stock.

from AlgorithmImports import *
from QuantConnect.DataSource import *

class TiingoNewsDataAlgorithm(QCAlgorithm):

    current_holdings = 0
    target_holdings = 0
    # Custom word-score map to assign score for each word in article
    word_scores = {'good': 1, 'great': 1, 'best': 1, 'growth': 1,
                   'bad': -1, 'terrible': -1, 'worst': -1, 'loss': -1}

    def initialize(self) -> None:
        self.set_start_date(2021, 1, 1)
        self.set_end_date(2021, 6, 1)
        self.set_cash(100000)
        
        # Requesting Tiingo news data to obtain the updated news articles to calculate the sentiment score
        self.aapl = self.add_equity("AAPL", Resolution.MINUTE).symbol
        self.tiingo_symbol = self.add_data(TiingoNews, self.aapl).symbol
        
        # Historical data
        history = self.history(self.tiingo_symbol, 14, Resolution.DAILY)
        self.debug(f"We got {len(history)} items from our history request")
        
        
    def on_data(self, slice: Slice) -> None:
        if slice.contains_key(self.tiingo_symbol):
            # Assign a sentiment score to the news article by the word-score map
            title_words = slice[self.tiingo_symbol].description.lower()
            score = 0
            for word, word_score in self.word_scores.items():
                if word in title_words:
                    score += word_score
            
            # Buy if aggregated sentiment score shows positive sentiment, sell vice versa
            if score > 0:
                self.target_holdings = 1
            elif score < 0:
                self.target_holdings = -1
        
        # Buy or short sell if the sentiment has changed from our current holdings
        if slice.contains_key(self.aapl) and self.current_holdings != self.target_holdings:
            self.set_holdings(self.aapl, self.target_holdings)
            self.current_holdings = self.target_holdings
public class TiingoNewsDataAlgorithm : QCAlgorithm
{
    private Symbol _aapl;
    private Symbol _tiingoSymbol;
    private int _currentHoldings = 0;
    private int _targetHoldings = 0;
    // Custom word-score map to assign score for each word in article
    private Dictionary<string, int> _wordScores = new Dictionary<string, int>(){
        {"good", 1}, {"great", 1}, {"best", 1}, {"growth", 1},
        {"bad", -1}, {"terrible", -1}, {"worst", -1}, {"loss", -1}
    };
    
    public override void Initialize()
    {
        SetStartDate(2021, 1, 1);
        SetEndDate(2021, 6, 1);
        SetCash(100000);
        
        // Requesting Tiingo news data to obtain the updated news articles to calculate the sentiment score
        _aapl = AddEquity("AAPL", Resolution.Minute).Symbol;
        _tiingoSymbol = AddData<TiingoNews>(_aapl).Symbol;
        
        // Historical data
        var history = History<TiingoNews>(_tiingoSymbol, 14, Resolution.Daily);
        Debug($"We got {history.Count()} items from our history request");
    }
    
    public override void OnData(Slice slice)
    {
        if (slice.ContainsKey(_tiingoSymbol))
        {
            // Assign a sentiment score to the news article
            var titleWords = slice[_tiingoSymbol].Description.ToLower();
            var score = 0;
            foreach (KeyValuePair<string, int> entry in _wordScores)
            {
                if (titleWords.Contains(entry.Key))
                {
                    score += entry.Value;
                }
            }

            // Buy if aggregated sentiment score shows positive sentiment, sell vice versa
            if (score > 0)
            {
                _targetHoldings = 1;
            }
            else if (score < 0)
            {
                _targetHoldings = -1;
            }
        }
        
        // Buy or short sell if the sentiment has changed from our current holdings
        if (slice.ContainsKey(_aapl) && _currentHoldings != _targetHoldings)
        {
            SetHoldings(_aapl, _targetHoldings);
            _currentHoldings = _targetHoldings;
        }
    }
}

Framework Algorithm Example

The following example algorithm assigns a sentiment score to each news article that's released for Apple. When the sentiment score is positive, the algorithm buys Apple stock. When the sentiment score is negative, it short sells Apple stock. The algorithm holds positions for 14 days.

from AlgorithmImports import *
from QuantConnect.DataSource import *

class TiingoNewsDataAlgorithm(QCAlgorithm):

    def initialize(self) -> None:
        self.set_start_date(2021, 1, 1)
        self.set_end_date(2021, 6, 1)
        self.set_cash(100000)
        
        symbols = [Symbol.create("AAPL", SecurityType.EQUITY, Market.USA)]
        self.add_universe_selection(ManualUniverseSelectionModel(symbols))
        self.add_alpha(TiingoNewsAlphaModel())
        self.set_portfolio_construction(EqualWeightingPortfolioConstructionModel())

 
class TiingoNewsAlphaModel(AlphaModel):
    
    current_holdings = 0
    target_holdings = 0
    # Custom word-score map to assign score for each word in article
    word_scores = {'good': 1, 'great': 1, 'best': 1, 'growth': 1,
                   'bad': -1, 'terrible': -1, 'worst': -1, 'loss': -1}
    
    def update(self, algorithm: QCAlgorithm, slice: Slice) -> List[Insight]:
        if slice.contains_key(self.tiingo_symbol):
            # Assign a sentiment score to the news article by the word-score map
            title_words = slice[self.tiingo_symbol].description.lower()
            score = 0
            for word, word_score in self.word_scores.items():
                if word in title_words:
                    score += word_score

            # Buy if aggregated sentiment score shows positive sentiment, sell vice versa
            if score > 0:
                self.target_holdings = 1
            elif score < 0:
                self.target_holdings = -1
        
        # Buy or short sell if the sentiment has changed from our current holdings
        if slice.contains_key(self.aapl) and self.current_holdings != self.target_holdings:
            self.current_holdings = self.target_holdings
            direction = InsightDirection.UP if self.target_holdings == 1 else InsightDirection.DOWN
            return [Insight.price(self.aapl, timedelta(days=14), direction)]
            
        return []
        
        
    def on_securities_changed(self, algorithm: QCAlgorithm, changes: SecurityChanges) -> None:
        for security in changes.added_securities:
            self.aapl = security.symbol
            
            # Requesting Tiingo news data to obtain the updated news articles to calculate the sentiment score
            self.tiingo_symbol = algorithm.add_data(TiingoNews, self.aapl).symbol
                
            # Historical data
            history = algorithm.history(self.tiingo_symbol, 14, Resolution.DAILY)
            algorithm.debug(f"We got {len(history)} items from our history request")
public class TiingoNewsDataAlgorithm : QCAlgorithm
{

    public override void Initialize()
    {
        SetStartDate(2021, 1, 1);
        SetEndDate(2021, 6, 1);
        SetCash(100000);
        
        var symbols = new[] {QuantConnect.Symbol.Create("AAPL", SecurityType.Equity, Market.USA)};
        AddUniverseSelection(new ManualUniverseSelectionModel(symbols));
        AddAlpha(new TiingoNewsAlphaModel());
        SetPortfolioConstruction(new EqualWeightingPortfolioConstructionModel());
    }
    
    public class TiingoNewsAlphaModel : AlphaModel
    {
        private Symbol _aapl;
        private Symbol _tiingoSymbol;
        private int _currentHoldings = 0;
        private int _targetHoldings = 0;
        // Custom word-score map to assign score for each word in article
        private Dictionary<string, int> _wordScores = new Dictionary<string, int>(){
            {"good", 1}, {"great", 1}, {"best", 1}, {"growth", 1},
            {"bad", -1}, {"terrible", -1}, {"worst", -1}, {"loss", -1}
        };

        public override IEnumerable<Insight> Update(QCAlgorithm algorithm, Slice slice)
        {
            var insights = new List<Insight>();
            
            if (slice.ContainsKey(_tiingoSymbol))
            {
                // Assign a sentiment score to the news article by the word-score map
                var titleWords = slice[_tiingoSymbol].Description.ToLower();
                var score = 0;
                foreach (KeyValuePair<string, int> entry in _wordScores)
                {
                    if (titleWords.Contains(entry.Key))
                    {
                        score += entry.Value;
                    }
                }

                // Buy if aggregated sentiment score shows positive sentiment, sell vice versa
                if (score > 0)
                {
                    _targetHoldings = 1;
                }
                else if (score < 0)
                {
                    _targetHoldings = -1;
                }
            }
            
            // Buy or short sell if the sentiment has changed from our current holdings
            if (slice.ContainsKey(_aapl) && _currentHoldings != _targetHoldings)
            {
                _currentHoldings = _targetHoldings;
                var direction = _targetHoldings == 1 ? InsightDirection.Up : InsightDirection.Down;
                insights.Add(Insight.Price(_aapl, TimeSpan.FromDays(14), direction));
            }
            
            return insights;
        }

        public override void OnSecuritiesChanged(QCAlgorithm algorithm, SecurityChanges changes)
        {
            foreach (var security in changes.AddedSecurities)
            {
                _aapl = security.Symbol;
                
                // Requesting Tiingo news data to obtain the updated news articles to calculate the sentiment score
                _tiingoSymbol = algorithm.AddData<TiingoNews>(_aapl).Symbol;
        
                // Historical data
                var history = algorithm.History<TiingoNews>(_tiingoSymbol, 14, Resolution.Daily);
                algorithm.Debug($"We got {history.Count()} items from our history request");
            }
        }
    }
}

Data Point Attributes

The Tiingo News Feed dataset provides TiingoNews objects, which 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: