Amazon.com

About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Computer science & Service (business). The organization has 13363 authors who have published 17317 publications receiving 266589 citations.

MAFIA: a maximal frequent itemset algorithm

Abstract: We present a new algorithm for mining maximal frequent itemsets from a transactional database. The search strategy of the algorithm integrates a depth-first traversal of the itemset lattice with effective pruning mechanisms that significantly improve mining performance. Our implementation for support counting combines a vertical bitmap representation of the data with an efficient bitmap compression scheme. In a thorough experimental analysis, we isolate the effects of individual components of MAFIA including search space pruning techniques and adaptive compression. We also compare our performance with previous work by running tests on very different types of data sets. Our experiments show that MAFIA performs best when mining long itemsets and outperforms other algorithms on dense data by a factor of three to 30.

Electronic gift certificate system

Abstract: An electronic gift certificate system is disclosed which distributes electronic gift certificates in the form of e-mail documents that include hyperlinks for automating the redemption process. When a gift certificate recipient selects such a hyperlink, the recipient's computer automatically transmits a claim code to the merchant's Web site, and the site responds by automatically crediting the recipient's personal account with the gift certificate amount. When the recipient subsequently makes a purchase from the merchant's Web site, the recipient's account balance is automatically applied to the purchase price.

Detecting and Correcting for Label Shift with Black Box Predictors

Abstract: Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets) cause symptoms (observations), we focus on label shift, where the label marginal $p(y)$ changes but the conditional $p(x| y)$ does not. We propose Black Box Shift Estimation (BBSE) to estimate the test distribution $p(y)$. BBSE exploits arbitrary black box predictors to reduce dimensionality prior to shift correction. While better predictors give tighter estimates, BBSE works even when predictors are biased, inaccurate, or uncalibrated, so long as their confusion matrices are invertible. We prove BBSE's consistency, bound its error, and introduce a statistical test that uses BBSE to detect shift. We also leverage BBSE to correct classifiers. Experiments demonstrate accurate estimates and improved prediction, even on high-dimensional datasets of natural images.

Method and apparatus for a searchable data service

Abstract: A searchable data service implementation may include, but is not limited to, a Web services platform (200), one or more coordinator nodes (350), one or more query nodes, referred to as query TSAR (Top Search AggregatoR) nodes (360), and one or more storage nodes (370). Each coordinator node (350) may include, but is not limited to, at least one instance of request router (202). A client system (330) may submit service requests (query node requests and/or storage node requests) to the searchable data service in accordance with the Web service interface of the Web services platform (200) via Internet (334). The Web services platform (200) may route the service request (s) to a coordinator node (350). A coordinator node (350) routes the service requests to the appropriate node(s) , collects result, and send the results back to the web services platform (200). A request router on the coordinator node (350) may receive the service request (s) from the Web services platform (200) and determine whether each service request is a storage node request or a query node request.