adobe / adobe/xdm

Add predictive send time and predictive fatigue to Standard Schema

Open
#247 3 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
JavaScript
Stars
266
Forks
380
Avg merge
5d 8h
Merged PRs (30d)
9

Description

## What are the schemas that are affected by the issue - Profile

## What are examples of products that are impacted by the issue - Campaign (real time orchestration).

**Predictive Fatigue** is the probability between 0 and 1 that a customer would unsubscribe. One score per profile.
**Predictive send time for open** is the best time a communication must be sent to the customer to maximize opens. An array of 168 (24*7) elements with the probability that a customer will open at this time.
**Predictive send time for click** is the best time a communication must be sent to the customer to maximize clicks. An array of 168 (24*7) elements with the probability that a customer will click at this time.

Business Value: Making predictive fatigue and predictive send time available to marketers helps them decide whether they should send a message and what time they should send a message. This enables marketers to make data driven decisions therefore increasing engagement with their subscribers. This in turn helps Adobe Campaign differentiate itself from its competitors by being the solution that helps marketers increase revenue through ML algorithms.

Problem + Solution: Marketers currently send their messages at a time based on their intuition . IN addition they optimize for segments - not individuals. These attributes will help the marketer make decisions for each profile by using their digital behavior data. **To be used as an industry standard.**

Contributor guide

Open the contributing guide

Research direction

The issue identifies the Profile schema and Campaign real-time orchestration as affected areas, but names no files or tests. Start by locating the Profile schema and reviewing how profile-level predictive attributes are represented. Done means the schema defines predictive fatigue plus the 168-element open and click send-time probability arrays.

Written by the indexing model from the issue text.

Assessment

Domain
data
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.