How transportation and QSR companies leverage predicted end times
What is the current problem with predicting end times?
As it stands, there is virtually no readily available information to give people an idea of when sporting events will wrap up. If you’re just attending the game, not knowing an exact end time isn’t the end of the world. But if you’re operating a rideshare business and looking to mitigate unexpected demand surges, you want to know when the nearest football stadium will be emptying so that you can ensure you have enough drivers in that location. Similarly, if you’re creating a staffing schedule for a bar and you don’t know about a baseball game occurring down the block, you might get slammed when a huge influx of patrons come in to celebrate the big win.
By having insight into the most likely end times for sporting events, businesses that see demand shift when fans are watching games can better plan for increases and decreases in demand. That means better inventory management, staffing optimization, and promotional strategies. See below for an example of the predicted end time field returned in our events API.
You could try predicting the end time yourself, but this would be tricky to do accurately without robust machine learning models. PredictHQ’s Predicted End Times was built from years of historical data which takes into account the specific sport, how the current season is going, and which teams are playing to determine how long a game is likely to last. We offer Predicted End Times coverage for major sports. Supported sports are football, baseball, basketball, Ice-hockey, NASCAR, and soccer. For many games, we also update our database with actual end times after a game finishes to give you the most accurate historical data possible.
How can you benefit from Predicted End Times?
Rideshare and Mobility businesses:
Say you are an operations manager for a scooter business in a big city. You know that baseball games cause surges in demand for scooters since they help fans travel between the stadium and public transit stops. If you’re trying to optimize where to place scooters to accurately meet demand, you’re going to want to know exactly when a game will let out. This way, you can ensure there are ample scooters available outside the stadium exactly when the game ends, and that you’re not taking away scooters from other high-demand areas too early.
Quick Serve Restaurants and Bars:
If you’re in charge of staffing for a sports bar chain near a football stadium, it’s important to know the game schedule well in advance to make sure you have enough bar staff rostered on at the correct times. If spectators come in to celebrate a win or commiserate a loss, you want to optimize the staff roster so that you’re not wasting resources before the fans actually come in.
These are just some of the use cases that could benefit from Predicted End Times data, but there are many ways you can increase revenue opportunities while reducing operational costs with demand intelligence.
The technical details
The events endpoint of the PredictHQ API has been updated with changes for the Predicted End times feature:
You can now sort events on the predicted end time value by using the sort parameter with a value of predicted_end or -predicted_end.
You can filter on predicted end times by specifying a date range with the predicted_end.* parameter (see the filter parameter documentation).
The Predicted end time is returned as the predicted_end field in the events response data. This field will only be present if an actual end time is not available for the event and we have a predicted end time. The predicted end date of the event is in ISO 8601 format.
Note: Predicted end time and all other start and end times are in UTC if the event time zone is provided, and in local time otherwise. For example, Independence Day falls on the 4th of July regardless of the time zone and will have a null time zone.
See the PredictHQ Developer documentation for more details.
How to use the API
If an event does not have a valid end time then the predicted_end field will be present in the response. To use Predicted End Times you can implement logic that checks if the predicted_end field is present. The logic should be:
If the predicted_end field is present then use the predicted_end field value for the event end time
If the predicted_end field is not present use the end field for the event end time.
You can also use the sort parameter to sort by the end time and the predicted_end where needed.
To learn more about what you can accomplish with demand intelligence data, sign up for a free trial or contact us.