官术网_书友最值得收藏!

Deploying models

Once we generate a model that abides by our initial KPI requirements, we need to deploy it in the production environment. This could be something as simple as creating a list of neighborhoods and political issues to address in each neighborhood, or something as complex as shipping the model to thousands of machines to make real-time decisions about which advertisements to buy for a particular marketing campaign. Once deployed to production, it is important to keep on monitoring those KPIs to make sure we're still solving the problem we aimed at initially. Sometimes, the model could have negative effects due to a change in trends, and another model needs to be trained. For instance, listeners over time may lose interest in continually hearing the same music style and the process must start all over again.

主站蜘蛛池模板: 弥渡县| 武城县| 深泽县| 芜湖市| 同仁县| 大理市| 电白县| 阳城县| 清原| 神木县| 沂南县| 辽宁省| 卢湾区| 石家庄市| 久治县| 惠来县| 怀仁县| 醴陵市| 临西县| 凌云县| 昌黎县| 闵行区| 新干县| 武安市| 中江县| 丰台区| 邵阳县| 临城县| 榆社县| 厦门市| 家居| 岱山县| 金阳县| 万山特区| 青铜峡市| 奇台县| 宝兴县| 蒙山县| 潜江市| 靖安县| 无棣县|