Trend prediction

A method of training a machine learning (ML) model for predicting trends, the method executed by a computer coupled with one or more processors and a memory for storing instructions executable by the one or more processors, the method comprising:

• generating, by the one or more processors, a ML model by:
• obtaining, by the one or more processors, trend data from one or more sources, the trend data including information about a plurality of trending posts as respectively defined by the one or more sources, each trending post in the plurality corresponding to one or more trends that trended at a prior time but that are not trending currently;
• extracting, by the one or more processors, a plurality of trends from the trend data;
• obtaining, by the one or more processors, contextual data that is indicative of a correlating factor explaining a reason why the one or more trends trended at the prior time but are not trending currently;
• deriving, by the one or more processors, training data based on the trend data and the contextual data;
• training, by the one or more processors, the ML model using one or more predictive algorithms based on the training data to predict trends based on trend data and contextual data to produce predicted trends;
• and
• altering, by the one or more processors, the one or more predictive algorithms based on comparing the predicted trends to actual trend results to improve accuracy of the one or more predictive algorithms.