A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instruction stored therein, the computer-executable program code instructions comprising program code instructions configured to:
- transmit respective electronic communications to a plurality of user devices at respective transmission times;
- track clickstream data generated by a plurality of user device interactions associated with the respective electronic communications to determine respective electronic communication access event times associated with respective instances for accessing content of the respective electronic communications;
- determine time to open data based on the respective transmission times and the respective electronic communication access event times, wherein the time to open data is indicative of respective time to open terms that begin at the respective transmission times and end at the respective electronic communication access event times;
- train, based at least in part on the time to open data, a machine learning model to determine a predicted time distribution of predicted time to open data indicative of respective predicted times associated with an electronic communication being accessed via a user device, wherein the respective predicted times correspond to a predicted interval of time that begins at transmission of the electronic communication to the user device and ends at access of the electronic communication via the user device;
- determine, based on the predicted time distribution, respective access scores for the electronic communication being accessed via the user device at the respective times, wherein the computer-executable program code instructions comprise program code instructions configured to determine the predicted time distribution by at least:
- generating a feature vector based on the clickstream data;
- and
- determining, based on training the machine learning model with the training data set and the feature vector, the predicted time distribution as a function of the feature vector;
- determine, based on the respective access scores associated with the predicted time distribution and data associated with one or more times the communication content has been provided to the user device, a freshness score defining user access probability for a subsequent electronic communication comprising the communication content;
- store the freshness score in a database;
- generate a relevance score for the communication content in response to a search request being received;
- apply the freshness score associated with the predicted time distribution to the relevance score to generate an updated relevance score;
- rank a plurality of communication content sets comprising at least the communication content based on respective updated relevance scores to generate ranked communication content;
- and
- return a subset of the ranked communication content.