Investigate the book details page of Douban reading, [People who like this book also like this] The effect of the recommended module, let’s take a look~
Basic user behavior analysis
The operation of the user’s recommendation list for [People who liked this book also liked] is as follows.
The user does not click on the recommended book, indicating that the user is not satisfied and does not like it; the user clicks on the recommended book, but there is a Thailand Phone Number jump-out behavior, indicating that the user is general about the recommendation; and there is viewing behavior, indicating that the user has a certain interest in the recommended book, more Satisfaction; if the user has interactive behavior and purchase behavior, it is considered that the user is satisfied, and an ideal recommendation effect is achieved.
Quantification of core indicators
Generally speaking, the measurement indicators of the ideal state of the recommender system are the precision rate and the recall rate. Accuracy is for our predictions, it shows how many of the predicted positive samples are actually positive samples. The recall rate is for our original sample, which indicates how many positive examples in the sample are predicted correctly.