Felix Zhou | Shopping, Weiran Li | Shopping, Somnath Banerjee | Shopping
Felix Zhou | 购物，李伟然| 购物，Somnath Banerjee | 购物
Pinterest’s mission is to bring everyone the inspiration to create a life they love. Shopping is at the core of Pinterest’s mission by helping Pinners find and purchase the products they like. Oftentimes when Pinners want to buy something, they are not aware that they can go to a product-only feed, where every Pin is a product from a trustworthy merchant. To increase awareness, we present an explicit portal to this product-only page in the main search results, which we refer to as “shopping upsells” (Fig.1, highlighted in the pink box). Showing upsells to non-shoppable queries like “how to make a mask” is a poor Pinner experience; this shopping upsell appears only when the search query shows high shopping intent, e.g., “white dress”.
Pinterest使命是带给每个人灵感，创造他们热爱的生活。 通过帮助Pinners查找和购买他们喜欢的产品，购物是Pinterest使命的核心。 通常，当Pinners想要购买东西时，他们并不知道他们可以去仅产品的提要，那里的每个Pin都是来自值得信赖的商人的产品。 为了提高知名度，我们在主要搜索结果中为该仅产品页面提供了一个明确的门户，我们将其称为“购物加售”(图1，粉色框中突出显示)。 对无法购物的查询(例如“如何制作面具”)显示加价销售是糟糕的Pinner体验； 仅当搜索查询显示出较高的购物意愿(例如“白色礼服”)时，此购物加售才会出现。
As it may be fairly straightforward to decide if a shopping upsell is appropriate for each search query on a case-by-case basis, it is a nontrivial task to scale it to hundreds of millions of daily searches on Pinterest. To address searches of this scale, we trained a high accuracy machine learning model to determine the query shopping intent, namely, if Pinners would like to shop when they search for this query. We also optimized the model serving by a combination of online and offline inference to reduce the latency and the infra cost.
由于要根据个案情况确定购物追加销售是否适合每个搜索查询可能非常简单，因此将其扩展到Pinterest上的每日搜索量达到亿万美元是一项艰巨的任务。 为了解决这种规模的搜索，我们训练了一种高精度的机器学习模型来确定查询的购物意图，即，当Pinners搜索此查询时是否愿意购物。 我们还通过结合在线和离线推理来优化模型服务，以减少延迟和基础设施成本。
购物意向模型 (Shopping Intent model)
What’s the query shopping intent? Different interpretations lead to different models. We firstly interpreted it as the upsell click rate (V1 model).Then we proposed to interpret it as the product Pin long click propensity (V2 model), which mitigated the issues of the V1 model.
查询购物意图是什么？ 不同的解释导致不同的模型。 我们首先将其解释为加售点击率(V1模型)，然后我们将其解释为产品Pin长点击倾向(V2模型)，从而缓解了V1模型的问题。
V1模型 (V1 Model)
The V1 model characterized the query shopping intent as the click rate of the upsell for a given query. The higher the upsell click rate, the more likely the query has the shopping intent. At the very beginning, we didn’t have any training data because there was no shopping upsell displayed. To collect the training data, we randomly displayed upsells for queries within a small portion of production traffic.
V1模型将查询购物意图表征为给定查询的加售点击率。 加售点击率越高，查询具有购物意图的可能性就越大。 最初，我们没有任何培训数据，因为没有显示购物追加销售。 为了收集培训数据，我们在少量生产流量中随机显示了加价查询。
For the collected training data, we defined the feature as the raw query and the label as the upsell click rate. To train the model, we used a 100 dimension pre-trained embedding to featurize the queries and built a three-layer vanilla deep neural network to train a binary cross-entropy model. The model output is the predicted upsell click rate.
对于收集的训练数据，我们将功能定义为原始查询，将标签定义为加售点击率。 为了训练该模型，我们使用了100维预训练的嵌入来使查询特征化，并建立了一个三层的香草深层神经网络来训练一个二进制交叉熵模型。 模型输出是预测的加售点击率。
The upsell click rate-based model has two disadvantages:
基于加售点击率的模型有两个缺点：
- False positive signal: We observed that many times users clicked upsells without any engagement with the pins on the shopping search page. It indicated that either the users had no shopping intent and they accidentally clicked the upsell, or the search quality on the shopping page was not good. In either case, we should not trigger the upsell because it does not achieve the desired engagement outcome. 误报：我们观察到用户多次点击加价广告，而没有与购物搜索页面上的图钉进行任何互动。 它表明用户要么没有购物意图，要么无意中点击了加售，或者购物页面上的搜索质量不佳。 无论哪种情况，我们都不应触发加售，因为它不能达到预期的参与效果。
- Biased feedback loop of the positive signal: All the positive signals came from the clicked upsells predicted by models in the past. A newer version of the model just tried to fit the signal from the past. 正信号的偏置反馈环路：所有正信号均来自模型过去预测的点击加售。 该模型的更新版本只是试图适应过去的信号。
To address both issues, we switched to an improved V2 model.
为了解决这两个问题，我们改用了改进的V2模型。
V2模型 (V2 Model)
Pinterest shows product Pins on both the shopping upsell and the organic search page, but we don’t show price tags for product Pins on the organic search page. Based on users’ engagement with product Pins, strong signals indicate whether users are interested in shopping: users may save the Pin to a board or click through the Pin to visit the associated website and remain offsite for an extended period of time (called ‘long click’ in Pinterest). In the V2 model, we characterize the query shopping intent as the long click propensity of product Pins for a query.
Pinterest在购物追加销售和自然搜索页面上都显示了产品图钉，但我们没有在自然搜索页面上显示产品图钉的价格标签。 根据用户对产品Pins的参与程度，强烈的信号表明用户是否对购物感兴趣：用户可以将Pins保存到板上或单击Pins来访问关联的网站，并长时间不在现场(称为“长时间”在Pinterest中点击”)。 在V2模型中，我们将查询购物意图表征为查询的产品图钉的长按倾向。
For a search query, we define the long click propensity as
对于搜索查询，我们将长点击倾向定义为
Where
哪里
and
和
We use the save signal to calculate the long click propensity because (1) save is like add-to-cart on shopping websites and users may save Pins for future purchases and (2) it can generate more training samples and further break the feedback loop. We trained a model defined in Fig 2.
我们使用保存信号来计算长时间点击的倾向，因为(1)保存就像购物网站上的购物车中的购物车一样，用户可能会保存销钉以备将来购买；(2)它可以生成更多的训练样本并进一步打破反馈循环。 我们训练了图2中定义的模型。
模型服务 (Model serving)
To reduce the infra cost of serving a deep learning model, we don’t call the model for the following queries:
为了降低服务深度学习模型的基础设施成本，我们不为以下查询调用该模型：
- Head queries, which contribute one third of our yearly search traffic: Wrong predictions on the head queries have worse impact than on the non-head queries. While we can not ensure 100% predicting accuracy, we precompute the shopping intent scores for the head queries and retain the scores in a key-value storage where the lookup latency is on the millisecond level. 头查询占我们年度搜索流量的三分之一：头查询的错误预测比对非头查询的影响更糟。 尽管我们无法确保100％的预测准确性，但我们会预先计算头查询的购物意图得分，并将得分保留在键值存储中，其中查找延迟为毫秒级。
- Queries belonging to the non-shoppable categories, such as ‘recipe’ or ‘finance’: We leverage the existing query to product category model in production to filter those queries. 属于不可购物类别(例如“食谱”或“财务”)的查询：我们将现有查询用于生产中的产品类别模型以过滤这些查询。
After filtering, we reduced 70% traffic to the deep learning model. Fig. 3 shows the whole workflow.
过滤后，我们将深度学习模型的流量减少了70％。 图3显示了整个工作流程。
影响力 (Impact)
After launching the experiment, the model increased more than 2X traffic to the shopping search page without hurting overall search metrics in terms of long clicks or saves. The model also increased more than 2X product impressions and product long clicks through the upsell.
启动实验后，该模型增加了购物搜索页面访问量的2倍以上，而不会因长期点击或保存而损害整体搜索指标。 该模型还增加了2倍以上的产品展示次数和2次产品长期点击次数。
Displaying shopping upsells for high shopping intent queries is just one of the strategies to acquaint users with Pinterest shopping. In the future, we will incorporate more signals to improve the model performance, helping more users enjoy shopping on Pinterest.
为高购物意图查询显示购物加售只是使用户熟悉Pinterest购物的策略之一。 将来，我们将结合更多信号来改善模型性能，帮助更多用户享受Pinterest购物。
Acknowledgments: The author would like to thank the following people for their contributions — Jinyu Xie, Karthik Anantha Padmanabhan and Tien Nguyen.
致谢：作者要感谢以下人士的贡献-谢金雨，Karthik Anantha Padmanabhan和Tien Nguyen。
翻译自: https://medium.com/pinterest-engineering/driving-shopping-upsells-from-pinterest-search-d06329255402
扫一扫
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
