Maximum likelihood estimation under a covariance constraint for predictive modeling
US8275656B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Mar 11, 2010 |
| Grant date | Sep 25, 2012 |
| Priority date | — |
| Expiry date | Dec 27, 2030 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06Q30/0254
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments employ a maximum likelihood estimation (MLE) under a covariance matrix floor constraint to predict missing data from observed data. An MLE solution is obtained for approximately Gaussian distributions under the constraint that the covariance matrix is greater than or equal to a positive-definite matrix. In one embodiment, an offline model estimation is performed using an expectation-maximization (EM) approach to estimate various statistical parameters based on observed data. Then, in an online approach, parameters for various missing CTR data may be predicted based on the offline estimated statistical parameters. A non-limiting, non-exhaustive example using the constrained MLE approach is described for predicting missing click-through rate data useable in selecting an advertisement to display with a search query result.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.