官术网_书友最值得收藏!

Evaluation metrics

Before applying an ML algorithm, we need to consider how to assess the effectiveness of our strategy. In some cases, we can use part of our data to simulate the performance of the algorithm. However, on other occasions, the only viable way to evaluate the application of an algorithm is by doing some controlled testing (A/B testing) and determining whether the use cases in which the algorithm was applied resulted in a better outcome. In our music streaming example, this could mean selecting a panel of users and recommending songs to them using the new algorithm. We can run statistical tests to determine whether these users effectively stayed longer on the platform. Evaluation metrics should be determined based on the business KPIs and should show significant improvement over existing processes.

主站蜘蛛池模板: 阿巴嘎旗| 内乡县| 焦作市| 蓝山县| 凤台县| 和林格尔县| 姜堰市| 房产| 吉水县| 清水河县| 张掖市| 友谊县| 光山县| 鄂托克前旗| 资源县| 东乡| 祁东县| 乌恰县| 泽州县| 苍山县| 甘谷县| 五原县| 莱西市| 五家渠市| 青浦区| 涟水县| 鱼台县| 东乡县| 北流市| 建水县| 镇安县| 同心县| 新乐市| 萨嘎县| 巴南区| 张掖市| 佛冈县| 临澧县| 资兴市| 周宁县| 台州市|