Impact Patterns
Also known as “Demand impact patterns”. This field shows the impact for leading days (days before the event), lagging days (days after an event), and the days the event occurs.
You can use Demand Impact Patterns in your demand forecasting so that your machine learning models will take account of the impact on leading and lagging days. In our testing we have found using impact patterns increases forecasting accuracy.
Vertical, type, and category mapping
Impact Patterns are available for the following industry segments and categories:
Vertical | Impact Type | Category |
---|---|---|
|
|
|
|
|
|
| ||
| ||
| ||
| ||
| ||
| ||
|
|
|
| ||
| ||
| ||
| ||
| ||
|
Impact Patterns in the Events API
Impact patterns are returned in the Events API response in the impact_patterns
field. This shows the Impact Pattern for each event. Below are the details of the data structure of that field.
impact_patterns
is an array of impact pattern objects. The same event can have different impact patterns for different industry verticals. It contains the following fields:
vertical
- The industry vertical the impact pattern applies to.impact_type
- Indicates the type of impact shown in the impact pattern. This will apply to eitherphq_rank
orphq_attendance
, depending on the vertical.
impacts
is an array of objects with one entry for each day that contains the following values:
date_local
- the date in the local timezone of the event.value
- the value of theimpact_type
for that given day. For example, if theimpact_type
wasphq_rank
the value would be the PHQ Rank value on the given day. In the case foraccommodation
orhospitality
where theimpact_type
isphq_attendance
, this is what will be presented in this field.position
- can beleading
,event_day
orlagging
.leading
are the days before the event occurs,event_day
are the days the event occurs, andlagging
are the days after the event has occurred.
or for retail
for severe weather events
Impact Patterns in the Features API
You can also use Demand Impact Patterns with the Features API. The features API provides pre-built machine learning features for demand forecasting. See the features API documentation. Use the features for your industry to get more accurate forecasting results. We have a generic feature without impact patterns for sports called phq_attendance_sports
but that does not include impact patterns so only shows the impact on the days of the event. In order to use impact patterns with the features API you need to use the impact pattern features. For example, if you are in the accommodation segment and are using the features API to find the impact of sports events on your location you would use phq_attendance_sports_accommodation
. If you were in the Hospitality Segment you would use phq_attendance_sports_hospitality
.
Last updated