Projects


Knowledge Acquisition and Management
The Knowledge Graph project aims to build and maintain a lightweight unified knowledge base of all the concepts and entities we care about at Yahoo. It provides key informations about entities and how they relate to each others. Continue reading
 
Yahoo Amoeba
Surpassing the usual paradigm of surfacing only the trending entities, Amoeba enables the users to explore why a particular entity is trending. It is a new application to discover trends in online conversations Continue reading
 
Political Hashtag Trends
Political Hashtag Trends by Yahoo Labs detects political hashtags trending in a given week and displays the proportion of times a hashtag was used by left- or right-leaning users, respectively marked in blue and red Continue reading
 
InStore
Shop using your mobile phone and scan products for product details Continue reading
 
Motif
Searching for something today on the Web will usually return reasonable results. But what if a system was given more information, such as context, for the search? Continue reading
 
The Predictalot Experiment for the World Cup
Predictalot, our crowdsourcing experiment, is going global. This time, you can predict almost anything your heart desires about the World Cup in South Africa, like whether Germany will advance further than Brazil or a team will win that has never won before. You can compose any of millions of predictions and sell them any time for virtual points, even in the middle of a match, just like the stock market. Continue reading
 
Pig
Parallel processing is the name of the game. Our system runs on a cluster computing architecture, on top of which sit several layers of abstraction that ultimately bring the power of parallel computing into the hands of ordinary users. Continue reading
 
Friend Sense
How well do you really know your friends? Guess their views on life, politics and relationships. Answer questions about yourself and find out who knows you best! Continue reading
 
CAPTCHAs
CAPTCHAs ensure that Yahoo properties are utilized by humans for the intended purposes to prevent email spam and phishing messages. Continue reading
 
Multimedia Search
Multimedia search on Yahoo helps people find what they are looking for through Web, image, or video search. One of the most interesting challenges is how to match queries to images beyond plain text so that users can more easily find the image they want. Continue reading
 
Traffic Shaping
Traffic shaping jointly optimizes CTR and post-click downstream utilities for recommending links. To achieve this goal, multiple objectives are modeled in a constrained optimization framework, aiming to taking revenue as an objective for content optimization. Continue reading
 
User-Generated Content Abuse Detection
The Yahoo Labs Audience Sciences team collaborates with the Yahoo abuse engineering team to build a standard moderation platform that automatically detects abusive user-generated content (UGC) in the major media properties of Yahoo Continue reading
 
Auction Anti-Fraud
The Yahoo Labs Audience Sciences team builds machine learning models into the fraud detection system to prevent fraud in Yahoo Auctions. Continue reading
 
User Reputation
Reputable users are valuable assets to Yahoo. The Yahoo Labs Audiences Sciences team examines user reputation in a comment rating environment, where users make comments about content and rate the comments of one another Continue reading
 
User Understanding
The Yahoo Labs Audience Science team works on user understanding to collect and leverage data about Yahoo users to provide more relevant content and search experiences. Continue reading
 
Copyright © 2014 Yahoo. All rights reserved.