Abstract: Methods and systems are described herein for incremental bidding for electronic advertisements. A computing device generates, for a user during a first time period, first randomized bids for available impression opportunities, the first randomized bids based upon an estimated value and a first random factor and using a context of bid requests. The computing device transmits the first randomized bids to a remote device. The computing device determines whether interaction events associated with impression opportunities occurred. The computing device estimates second randomized bids based upon an estimated value and a second random factor and using the context. The computing device estimates a relative incrementality of a bidding policy based upon the second randomized bids over a bidding policy based upon the first randomized bids, and optimizes the bidding policy based upon second randomized bids. The computing device changes a production bidding policy based upon the optimized policy.

Abstract: Methods and systems are described herein for incremental bidding for electronic advertisements. A computing device generates, for a user during a first time period, first randomized bids for available impression opportunities, the first randomized bids based upon an estimated value and a first random factor and using a context of bid requests. The computing device transmits the first randomized bids to a remote device. The computing device determines whether interaction events associated with impression opportunities occurred. The computing device estimates second randomized bids based upon an estimated value and a second random factor and using the context. The computing device estimates a relative incrementality of a bidding policy based upon the second randomized bids over a bidding policy based upon the first randomized bids, and optimizes the bidding policy based upon second randomized bids. The computing device changes a production bidding policy based upon the optimized policy.

Abstract: A computer accesses a multidimensional vector space that comprises embeddings of catalog item embeddings, each catalog item having one or more item attributes and corresponding item attribute values, and embeddings of associated item attribute values. An identification of one or more seed catalog items is received. Embeddings of each of one or more seed catalog items and embeddings of associated item attribute values are identified within the vector space. For each one of the seed catalog items, for each of the item attributes of the seed catalog item, an item representation in the vector space is located based upon a combination of the embedding of the seed catalog item and of an embedding of an item attribute value representing an item attribute value that is similar to the corresponding item attribute value of the seed catalog item. For each item representation, one or more embeddings of candidate catalog items that are close to the product representation are selected.