Yahoo! Inc.

Microsoft Technology Licensing, LLC

Fair Issac Corporation

Vijay Krishna Narayanan

Deepak Agarwal

John Thrall

Bee-Chung Chen

Sudarshan Raghunathan

Amitabh Seth

Raghu Ramakrishnan

Nitin Motgi

Walter Sun

Kin Fai Kan

Howard Scott Roy

Matthias Blume

Uwe Mayer

Pradheep K Elango

Vik Singh

Mayank Shrivastava

Gagan Bansal

Jiangyi Pan

Andrew Edward Kae

Debraj GuhaThakurta

Akshaya Annavajhala

Amita Surendra Gajewar

Joe Zachariah

Sharat Israni

Chandar Venkataraman

Amit Phadke

Konstantin Golyaev

Michael Salisbury

A multi-horizon predictor system that predicts a future parameter value for multiple horizons based on time-series data of the parameter, external data, and machine-learning. For a given time horizon, a time series data splitter splits the time into training data corresponding to a training time period, and a validation time period corresponding to a validation time period between the training time period and the given horizon. A model tuner tunes the prediction model of the given horizon fitting an initial prediction model to the parameter using the training data thereby using machine learning. The model tuner also tunes the initial prediction model by adjusting an effect of the external data on the prediction to generate a final prediction model for the given horizon using the validation data. A multi-horizon predictor causes the time series data splitter and the model tuner to operate for each of multiple horizons.

Predictive modeling across multiple horizons combining time series and external data

An interoperable platform that provides a way to automatically compose and execute even complex workflows without writing code is described. A set of pre-built functional building blocks can be provided. The building blocks perform data transformation and machine learning functions. The functional blocks have few well known plug types. The building blocks can be composed to build complex compositions. Interoperability between data formats, metadata schema and interfaces to machine learning (ML) functions and trained machine learning models can be provided with no loss of information. A cloud runtime environment can be provided in which the composed workflows can be hosted as REST API to run in production.

Interoperable machine learning platform

A system and method for automatically classifying ads into a taxonomy of categories, the method including: extracting text features from ad images using OCR (optical character recognition) techniques; identifying objects of interest from ad images using object detection and recognition techniques in computer vision; extracting text features from the web-page of the advertiser to which the user is re-directed when clicking the ad; training statistical models using the extracted features mentioned above as well as advertiser attributes from a historical dataset of ads labeled by human editors; and determining the relevant categories of unlabeled ads using the trained models.

Automatic classification of display ads using ad images and landing pages

A method and apparatus for customizing content presented to individual users or user segments is provided. There may be three components, a web portal and toolbar component, a modeling component, and a scoring component. The web portal and toolbar component presents content items and collects data. The web portal and toolbar component generates user event data based on the user actions. The user event data is forwarded to the modeling component. The modeling component generates content scoring functions based on user event data and attributes of content items. Content scoring functions may be unique to individual user segments. The content scoring functions based on content features generate probability a content item will be viewed. The scoring component decides which content items are placed in a portal. The scoring component uses the scoring functions generated by the modeling component to rank content items in real time.

Customized today module

The likelihood that a query belongs to a vertical is determined. The query is assigned to a vertical based on that likelihood. A query submitted to a main search box is assigned to verticals and processed using indices specific to those verticals. The query is assigned to verticals based on coverage adjusted log likelihood per unit (CALL) values for that query in those verticals. An offline learning component computes UNITS dictionaries and learns the distributions of query units in the main search and each of the vertical searches using query logs. An online scoring and ranking component uses the query distributions and UNITS dictionaries to determine the CALL values and a likelihood of the query belonging to any vertical. The search query is then assigned to verticals based on the likelihoods. The search query is then processed by all the verticals the query is assigned to.

Search query categrization into verticals

A computer-implemented technique for fuzzy matching. This works quickly yet accurately to determine if a given computer-readable record is represented, by exact match or pretty close match, in a large collection of computer-readable records. Further tools may be provided to assess the character of the match.

Fast accurate fuzzy matching

Growing community of inventors

Mountain View, CA, United States of America

Vijay Krishna Narayanan