Abstract
A method for email recommendation comprises obtaining a plurality of user features of a user and a plurality of email features of each of a plurality of emails. The method further comprises obtaining a plurality of weights for each email. Each of the plurality of weights is associated with a user feature or an email feature. The method further comprises determining a plurality of context vectors corresponding to the plurality of emails. Each context vector comprises a combination of the plurality of user features and the plurality of email features of a corresponding email. The method further comprises generating, via a machine learning model and based on the plurality of weights, a plurality of conversion probabilities corresponding to the plurality of context vectors. The method further comprises determining the context vector having the highest conversion probability and sending the corresponding email to the user.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Vedel, Søren; Sherveghar, Deepak Janardhan; Guillen, Rosa Maria Izquierdo; and Maersk A/S, "SYSTEM AND METHOD FOR EMAIL RECOMMENDATION", Technical Disclosure Commons, (January 23, 2025)
https://www.tdcommons.org/dpubs_series/7753