Jun J He

US Patent:

20220309523, Sep 29, 2022

Filed:

May 23, 2022

Appl. No.:

17/664601

Inventors:

- San Jose CA, US
Chang Liu - Piscataway NJ, US
Jun He - San Jose CA, US
Zhenyu Yan - San Jose CA, US
Wuyang Dai - Santa Clara CA, US
Shengyun Peng - San Jose CA, US

International Classification:

G06Q 30/02
G06Q 10/10
H04L 51/56

Abstract:

Introduced here are approaches for identifying the optimal send time for messages by accounting for hidden confounders, such as the content of those messages, delivery channel, etc. These approaches use a causal inference framework to discover and then remove the impact of hidden confounders. These approaches may be employed by a marketing and analytics platform (or simply “marketing platform”) that may be used to design, implement, or review digital marketing campaigns. The marketing platform can consider the send time as a treatment and then employ machine learning (ML) models that consider the send time, features of the recipient, and hidden confounders to produce a ranked series of send times with the effect of the hidden confounders marginalized. Approaches to performing offline evaluations that mimic A/B tests using data related to existing field experiments are also introduced here.

US Patent:

20210357952, Nov 18, 2021

Filed:

May 18, 2020

Appl. No.:

16/877385

Inventors:

- San Jose CA, US
Chang Liu - Piscataway NJ, US
Jun He - San Jose CA, US
Zhenyu Yan - San Jose CA, US
Wuyang Dai - Santa Clara CA, US
Shengyun Peng - San Jose CA, US

International Classification:

G06Q 30/02
G06Q 10/10
H04L 12/58

Abstract:

Introduced here are approaches for identifying the optimal send time for messages by accounting for hidden confounders, such as the content of those messages, delivery channel, etc. These approaches use a causal inference framework to discover and then remove the impact of hidden confounders. These approaches may be employed by a marketing and analytics platform (or simply “marketing platform”) that may be used to design, implement, or review digital marketing campaigns. The marketing platform can consider the send time as a treatment and then employ machine learning (ML) models that consider the send time, features of the recipient, and hidden confounders to produce a ranked series of send times with the effect of the hidden confounders marginalized. Approaches to performing offline evaluations that mimic A/B tests using data related to existing field experiments are also introduced here.