All Products
Search
Document Center

Artificial Intelligence Recommendation:Experiment effect analysis

Last Updated:Jul 17, 2023

After an experiment is started, you can view the business performance report of the experiment and perform decision-making operations on the experiment based on metric data. If the metric data shows that the experiment configurations provide better recommendation effect, you can apply the configurations of the current experiment to the default experiment. Otherwise, you can stop the experiment. For more information about the decision-making operations on experiments, see Experiment parameter settings.

Business Objectives:

PV_CTR: the click-through rate (CTR). Calculation formula: Total number of clicks/Total number of exposures. Duplicate records are counted.

UV_CTR: the proportion of users who click an item. Calculation formula: Number of users who click an item on a page/Total number of users who view the page.

PV_CVR: the conversion rate (CVR). Calculation formula: Number of purchases/Number of clicks.

UV_CVR: the proportion of converted users. Calculation formula: Number of users who purchase an item/Number of users who click the item.

User Popularity:

the number of daily active users and the number of monthly active users.

Overall Traffic Scale:

the total number of behavior such as exposing, clicking, adding to favorites, reviewing, adding to a cart, and purchasing.

Traffic CVR:

the favorite CVR, review CVR, and add-to-cart CVR.

Traffic Consumed per Person:

the number of exposures, the number of clicks, and the total number of behavior.

Business Performance Report

image.png