Frequently Asked Questions

Everything you need to know about our products + services.

Moments API - FAQ

What is the Moments API?
The Moments API is Buzzer’s proprietary technology solution enabling you to deliver the most exciting, LIVE moments directly to your fans.
Why do I need the Moments API?
The Moments API will automate the delivery of the most exciting, real time moments happening in venue. These automated moments are predictive (not just real-time) to ensure timeliness and include relevant, pertinent details that help to contextualize the moment, and then notify fans via alert at the precise time to allow them to experience the suspense and excitement live! Driving higher conversion rates and watch time of your content without the need for editorial support, saving time and resources.
What kind of data is available through the Moments API?
We identify, create, and deliver a variety of compelling Moments based on what’s happening with teams and players during the game, what bets are close to hitting or at risk of flopping, and what’s buzzing on social media.

Moments API - Technical FAQ

What is the input to this API?
Nothing! Just ping the API for a list of Moments that are live and active.
How often should I expect to ping the Moments API?
A Moment can happen at various points in the game and is both sparse and ephemeral by nature. Therefore, we recommend using push delivery to receive moments in real time. We also support polling, which should happen every 10-30 seconds while the event is in progress (on par with how often the game score might be updated on your platform) to ensure you receive the Moment as soon as we create and broadcast it, and can package it as you like before sending it off to your users.
How will this API improve in the future?
We’ll continue to expand on different sports/leagues, add additional Moment types such as those driven by social listening and sentiment, and continue to improve the breadth and scope of our existing Game, Player, and Betting Moments.

Personalization API - Technical FAQ

What is the input to the Personalization API?
Our Content Recommendations endpoint is designed to be used without user data. The only required input to the API is a desired “interest” that you want to find recommendations for. For example, a recommendation request based on ‘LaMelo Ball’ might return:
{
  "ranked_recommendations": [
    "Tyrese Haliburton",
    "Trae Young",
    "Ja Morant",
    "De'Aaron Fox",
    "Donovan Mitchell"
  ]
}

Which are all relevant to LaMelo Ball through things like position, style of play, rookie expectations, and other athlete attributes. With this list of recommendations, you can then determine which interests a user isn’t already subscribed to and push content involving these interests to further fuel the user’s discovery and engagement.

Our User Recommendations endpoint takes the above a step further and ingests your interest catalog along with your users’ preference and consumption data to crowdsource how a single user stacks up to the crowd, and ultimately what hyper-personalized recommendations they’re most likely to interact with. For example, you may provide a payload of NBA interests you serve on your platform:
{
  "interests": [
    "LeBron James",
    "Kevin Durant",
    "Chicago Sky",
    "Charlotte Hornets",
    "Sabrina Ionescu",
    ...
    "Ja Morant",
    "Paul George",
    "Phoenix Mercury",
    "Candace Parker",
    "Golden State Warriors"
  ]
}

along with a payload of your users and their defined interest or consumption data:
{
  "users": [
    {
      "id": "1h27l-17hd8-0d80e-nok91",
      "interests": [
        "Kevin Durant",
        "Klay Thompson",
        "Stephen Curry"
      ]
    },
    {
      "id": "8fhj4-jf01m-mn239-dmso7",
      "interests": [
        "Chelsea Gray",
        "Nneka Ogwumike",
        "Los Angeles Sparks",
        "Stephen Curry",
        "Boston Celtics"
      ]
    },
    ...
    {
      "id": "me8j1-la01g-54nk9-owqm7",
      "interests": [
        "Portland Trail Blazers",
        "Memphis Grizzlies"
      ]
    }
  ]
}

From here, our algorithms will do the math and learning to determine which content and interests you should push to each user based on the provided information. The output will look similar to the above input, except each list of returned interests will be recommendations specific to each individual user id provided:
{
  "users": [
    {
      "id": "1h27l-17hd8-0d80e-nok91",
      "ranked_recommendations": [
      	"Golden State Warriors",
        "Giannis Antetokounmpo",
        "Trae Young",
        "Los Angeles Lakers",
        "LeBron James"
]
    },
    {
      "id": "8fhj4-jf01m-mn239-dmso7",
      "ranked_recommendations": [
      	"Chiney Ogwumike",
        "Golden State Warriors",
        "Kevin Durant",
        "Los Angeles Lakers"
]
    },
    ...
    {
      "id": "me8j1-la01g-54nk9-owqm7",
      "ranked_recommendations": [
      	"Dallas Mavericks",
        "Philadelphia 76ers",
        "Chicago Bulls",
        "Brooklyn Nets",
        "Damian Lillard"
]
    }
  ]
}

With this user-level granularity, you can simply suggest a user follow these interests, or go so far as to passively curate and surface content around these hyper-personalized interests to drive more topic discovery.
Do I need to provide my proprietary user data?
For our Content Recommendations, your user data is not required.

For our User Recommendations, user data are required for our AI to crunch the numbers and provide a personalized set of recommendations specific to your users. That being said, these data can be anonymized — we don’t so much care who the user is, only that they have a certain content engagement behavior that we can mine to better understand and provide predictions on. So, ‘John Doe’ can be represented as ‘1h27l-17hd8-0d80e-nok91’ and all you need to do is remember this association so you can interpret our output within your tech stack. 

Please refer to “What is the input to the Personalization API?” above
Is there a Personalization API use case that doesn’t require user data?
Our Content Recommendations endpoint does not require user data — the only required input to the API is a desired “interest” that you want to find recommendations for. Please refer to “What is the input to the Personalization API?”

While this might not be hyper-personalized to the user’s existing interests and content consumption behavior (such as with the User Recommendations API), it is a simple first step toward facilitating more personalization and discovery on your platform.
How often will the recommendations from the Personalization API change?
Content Recommendations will change roughly every few days. Not all recommendations for every interest/topic are expected to change with every update, as this is very dependent on what is happening in the sports and social sphere. To this end, you should consider a data pipeline that only operates on observed changes from the API output, as opposed to a complete reloading of the output.

User Recommendations will only change as often as you provide user data, since our output is highly dependent on user-centric behavior and any changes made to your interest catalog. A good place to start is to base your interactions with our User Recommendations endpoint based on how frequently your new and existing users are updating their interests and interacting with the diverse content on your platform.
How often might I expect to ping the Personalization API?
For Content Recommendations, pinging the endpoint every 3-5 days for a specific topic is a good place to start, as this is how often we expect to see associations between different interests change based on sport, league, and social updates.

For User Recommendations, expect to ping the endpoint as often as you would like to provide updated user and catalog data for renewed user-centric recommendations.

Please refer to “How often will the recommendations from the Personalization API change?”
Can’t find the answer you’re looking for? Please chat with our team at contact@buzzer.com or book a demo below.
Book a Demo