Instacart
Assembly Line
How Instacart Uses Machine Learning to Suggest Replacements for Out-of-Stock Products
One of Instacartâs key challenges is predicting product availability without real-time inventory data. Our machine-learning model prompts replacement suggestions if a product appears unavailable when an Instacart customer shops. This replacement model also assists Instacart shoppers in selecting the best replacements during their shopping trips.
Our model uses a Siamese network that leverages identical weights to simultaneously process two different input vectors, creating output that can be easily compared. This configuration mirrors the classic âtwo-towerâ architecture prevalent in recommendation and search ranking applications. The product layer consolidates the four types of features mentioned above into an embedding representation for a product. The model employs a BERT-based sentence embedding layer to process product name text features, and embedded representations for high-cardinality categorical features are learned from scratch during model training.
How Instacart fixed its A.I. and keeps up with the coronavirus pandemic
Like many companies, online grocery delivery service Instacart has spent the past few months overhauling its machine-learning models because the coronavirus pandemic has drastically changed how customers behave.
Starting in mid-March, Instacartâs all-important technology for predicting whether certain products would be available at specific stores became increasingly inaccurate. The accuracy of a metric used to evaluate how many items are found at a store dropped to 61% from 93%, tipping off the Instacart engineers that they needed to re-train their machine learning model that predicts an itemâs availability at a store. After all, customers could get annoyed being told one thingâthe item that they wanted was availableâwhen in fact it wasnât, resulting in products never being delivered. âA shock to the systemâ is how Instacartâs machine learning director Sharath Rao described the problem to Fortune.