View source for Snap inc. (20240378638). PREDICTING A CONVERSION RATE simplified abstract

=PREDICTING A CONVERSION RATE=


==Organization Name==

[[:Category:snap inc.|snap inc.]]


[[Category:snap inc.]]

==Inventor(s)==

[[:Category:Weizhi Li of Freemont CA (US)|Weizhi Li of Freemont CA (US)]][[Category:Weizhi Li of Freemont CA (US)]]

[[:Category:Vineet Abhishek of San Mateo CA (US)|Vineet Abhishek of San Mateo CA (US)]][[Category:Vineet Abhishek of San Mateo CA (US)]]

[[:Category:Jason Brewer of Mountain View CA (US)|Jason Brewer of Mountain View CA (US)]][[Category:Jason Brewer of Mountain View CA (US)]]

[[:Category:Roman Grachev of Burlingame CA (US)|Roman Grachev of Burlingame CA (US)]][[Category:Roman Grachev of Burlingame CA (US)]]

[[:Category:Yugi Deng of Bellevue WA (US)|Yugi Deng of Bellevue WA (US)]][[Category:Yugi Deng of Bellevue WA (US)]]

[[:Category:David B. Lue of Santa Monica CA (US)|David B. Lue of Santa Monica CA (US)]][[Category:David B. Lue of Santa Monica CA (US)]]

==PREDICTING A CONVERSION RATE - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240378638 titled 'PREDICTING A CONVERSION RATE

'''Simplified Explanation:'''
The patent application describes a system and method for predicting the conversion rate of advertisements using machine learning.

* The system receives a bid from an advertisement service to display an advertisement on a computing device.
* It determines features related to the advertisement and provides them to a machine learning model.
* The machine learning model predicts the conversion rate based on the features, which have been trained using multi-task learning with sets of features from other advertisements.
* This predicted conversion rate helps in optimizing advertisement strategies.

'''Key Features and Innovation:'''
* Prediction of conversion rates for advertisements using machine learning.
* Training the machine learning model with sets of features from multiple advertisements.
* Optimization of advertisement strategies based on predicted conversion rates.

'''Potential Applications:'''
This technology can be used in digital marketing, online advertising, and e-commerce platforms to improve the effectiveness of advertisements.

'''Problems Solved:'''
* Predicting conversion rates accurately.
* Optimizing advertisement strategies.
* Enhancing the performance of online advertising campaigns.

'''Benefits:'''
* Improved targeting of advertisements.
* Higher conversion rates.
* Cost-effective advertising strategies.

'''Commercial Applications:'''
The technology can be utilized by digital marketing agencies, online retailers, and advertising platforms to increase the ROI of advertising campaigns.

'''Questions about Predicting Conversion Rates:'''
1. How does machine learning improve the accuracy of predicting conversion rates for advertisements?
2. What are the key factors considered by the machine learning model in predicting conversion rates?

'''Frequently Updated Research:'''
Stay updated on advancements in machine learning algorithms for predicting conversion rates in online advertising to enhance the effectiveness of marketing strategies.


==Original Abstract Submitted==

aspects of the present disclosure involve a system comprising a storage medium storing a program and method for predicting a conversion rate. the program and method provide for receiving, from an advertisement service, a bid to display a first advertisement at a computing device; determining, in response to receiving the bid, a set of features that relate to the first advertisement; providing the set of features to a machine learning model configured to output a predicted conversion rate for the first advertisement, the machine learning model having been trained based on multi-task learning using plural sets of features corresponding to plural second advertisements, the plural sets of features being associated with both click-through conversions and view-through conversions; and determining, based on the output of the machine learning model with respect to the set of features, the predicted conversion rate for the first advertisement.



[[Category:G06Q30/0242]]
[[Category:G06Q30/0241]]
[[Category:G06Q30/0273]]
[[Category:CPC_G06Q30/0246]]