Search

Your search keyword '"Anand, Radhika"' showing total 14 results
Start Over Author "Anand, Radhika"
14 results on '"Anand, Radhika"'

3. Maximum Relevance and Minimum Redundancy Feature Selection Methods for a Marketing Machine Learning Platform

Author

Zhao, Zhenyu, Anand, Radhika, and Wang, Mallory

Subjects
Statistics - Machine Learning, Computer Science - Machine Learning
Abstract

In machine learning applications for online product offerings and marketing strategies, there are often hundreds or thousands of features available to build such models. Feature selection is one essential method in such applications for multiple objectives: improving the prediction accuracy by eliminating irrelevant features, accelerating the model training and prediction speed, reducing the monitoring and maintenance workload for feature data pipeline, and providing better model interpretation and diagnosis capability. However, selecting an optimal feature subset from a large feature space is considered as an NP-complete problem. The mRMR (Minimum Redundancy and Maximum Relevance) feature selection framework solves this problem by selecting the relevant features while controlling for the redundancy within the selected features. This paper describes the approach to extend, evaluate, and implement the mRMR feature selection methods for classification problem in a marketing machine learning platform at Uber that automates creation and deployment of targeting and personalization models at scale. This study first extends the existing mRMR methods by introducing a non-linear feature redundancy measure and a model-based feature relevance measure. Then an extensive empirical evaluation is performed for eight different feature selection methods, using one synthetic dataset and three real-world marketing datasets at Uber to cover different use cases. Based on the empirical results, the selected mRMR method is implemented in production for the marketing machine learning platform. A description of the production implementation is provided and an online experiment deployed through the platform is discussed.

Published
2019

5. A model of the hepatorenal syndrome

Author

Anand, Radhika S.

Subjects
616.362
Abstract

Renal failure occurs in approximately 55% of patients with acute liver injury. Hepatorenal syndrome (HRS) is the development of renal failure secondary to liver disease in the absence of significant renal pathology. Presently there are no suitable models for the study of HRS. Recently, the rat model of galactosamine-induced acute liver failure (galn-ALF) was found to develop a hyperdynamic circulation along with a disruption in the renal haemodynamics which are characteristics of HRS. The aim of the project was to investigate the suitability of the rat model of galn-ALF as a model for HRS and to determine the role vasoactive mediators play in the pathogenesis of renal failure in this model. Characterisation of rats with galn-ALF showed that this was a suitable model for the study of HRS. The animals developed renal failure secondary to liver disease. The degree of renal impairment correlated with the degree of liver injury. The histology of the kidneys was normal and there was a reduction in the renal blood flow. A reduction in renal blood flow is indicative of renal vasoconstriction. Endothelin-1 (ET-1), a potent vasoconstrictor is elevated in patients with HRS. In the galn-ALF rat model of HRS ET-1 was found to be elevated in the plasma. In vitro autoradiography revealed that the ET-1 receptor ETA was upregulated in the renal cortex. Using the mixed receptor antagonist Bosentan in this model of HRS, renal function was improved. This suggests that elevated levels of ET-1 play a role in the pathogenesis of renal failure. Oxidant stress has also been found to play a role in renal failure. In the model there was marked lipid peroxidation. Oxidative stress was quantified by the measurement of F2- isoprostanes. These compounds are biologically active and can themselves cause renal vasoconstriction. Treatment with the anti-oxidants N-acetylcysteine and alpha-lipoic acid conferred some protection against renal impairment but was not effective in inhibiting lipid peroxidation. This suggests that a mechanism other than lipid peroxidation is involved in the renal dysfunction.

Published
2003

8. Taints

Author

Anand, Radhika

Published
2007

11. Trends in recording police interviews

Author

Anand, Radhika

Subjects
Law, Science and technology
Abstract

Consider the following scenario, which may sound familiar to many in law enforcement: A man is arrested in relation to a sexual assault investigation and questioned without a lawyer. After [...]

Published
2008

Catalog

Books, media, physical & digital resources
See catalog results