使用丰富的图像和文本数据对产品进行大规模分类

The last time we discussed product categorization on this blog, Shopify was powering over 1M merchants. We have since grown and currently serves millions of merchants who sell billions of products across a diverse set of industries. With this influx of new merchants, we decided to reevaluate our existing product categorization model to ensure we’re understanding what our merchants are selling, so we can build the best products that help power their sales.

上次我们在这个博客上讨论产品分类时，Shopify正在为超过100万个商家提供服务。此后，我们不断成长，目前为数百万商家提供服务，这些商家在不同的行业中销售数十亿的产品。随着新商家的涌入，我们决定重新评估我们现有的产品分类模型，以确保我们了解商家正在销售的产品，以便我们能够建立最好的产品，帮助他们的销售。

To do this, we considered two metrics of highest importance:

为了做到这一点，我们考虑了两个最重要的指标。

How often were our predictions correct? To answer this question, we looked at the precision, recall, and accuracy of the model. This should be very familiar to anyone who has prior experience with classification machine learning models. For the sake of simplicity let us call this set of metrics , “accuracy”. These metrics are calculated using a hold out set to ensure an unbiased measurement.
我们的预测有多少次是正确的？为了回答这个问题，我们看了模型的精度、召回率和准确率。对于任何有分类机器学习模型经验的人来说，这应该是非常熟悉的。为了简单起见，我们把这组指标称为 "准确性"。这些指标的计算是使用一个保留集，以确保无偏见的测量。
How often do we provide a prediction? Our existing model filters out predictions below a certain confidence thresholds to ensure we were only providing predictions that we were confident about. So, we defined a metric called “coverage”: the ratio of the number of products with a prediction and the total number of products.
我们多长时间提供一次预测？我们现有的模型会过滤掉低于一定信心阈值的预测，以确保我们只提供我们有信心的预测。因此，我们定义了一个叫做 "覆盖率 "的指标：有预测的产品数量与产品总数的比率。

In addition to these two metrics, we also care about how these predictions are consumed and if we’re providing the right access patterns and SLA’s to satisfy all use cases. As an example, we might want to provide low latency real time predictions to our consumers.

除了这两个指标外，我们还关心这些预测是如何被消费的，以及我们是否提供了正确的访问模式和SLA来满足所有的使用情况。举个例子，我们可能想为我们的消费者提供低延迟的实时预测。

After evaluating our model against these metrics and takin...