Arun K Ravindran

US Patent:

20220358404, Nov 10, 2022

Filed:

Apr 27, 2022

Appl. No.:

17/660911

Inventors:

- Boston MA, US
Arun Karthik RAVINDRAN - Somerville MA, US

Assignee:

The Boston Consulting Group, Inc. - Boston MA

International Classification:

G06N 20/00

Abstract:

Methods and systems of using reinforcement learning to optimizing promotions. A promotion can be offered to a user using a reinforcement learning model with a sensitivity parameter, the reinforcement module estimating a time period during which the user will respond to the first information. The user's reaction to the promotion can be observed. The reinforcement learning model can be adapted based on the user's reaction.

US Patent:

20200219012, Jul 9, 2020

Filed:

Feb 12, 2020

Appl. No.:

16/788495

Inventors:

- Dublin, IE
Arun Ravindran - Somerville MA, US
Anu Tayal - Chandigarh, IN
Naga Viswanath - London, GB
Lisa X. Wilson - Chicago IL, US

International Classification:

G06N 20/00
G06N 5/04

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for engineering a data analytics platform using machine learning are disclosed. In one aspect, a method includes the actions of receiving data indicating characteristics of data for analysis, analysis techniques to apply to the data, and requirements of users accessing the analyzed data. The actions further include accessing provider information that indicates computing capabilities of a respective data analysis provider, analysis techniques provided by the respective data analysis provider, and real-time data analysis loads of the respective data analysis provider. The actions further include applying the characteristics of the data, the analysis techniques, the requirements of the users, and the provider information, the analysis techniques, and the real-time data analysis loads to a model. The actions further include configuring the one or more particular data analysis providers to perform the analysis techniques on the data.

US Patent:

20190130313, May 2, 2019

Filed:

Aug 31, 2018

Appl. No.:

16/120140

Inventors:

- Dublin, IE
Arun Ravindran - Somerville MA, US
Anu Tayal - Chandigarh, IN
Naga Viswanath - London, GB
Lisa X. Wilson - Chicago IL, US

International Classification:

G06N 99/00
G06N 5/04

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for engineering a data analytics platform using machine learning are disclosed. In one aspect, a method includes the actions of receiving data indicating characteristics of data for analysis, analysis techniques to apply to the data, and requirements of users accessing the analyzed data. The actions further include accessing provider information that indicates computing capabilities of a respective data analysis provider, analysis techniques provided by the respective data analysis provider, and real-time data analysis loads of the respective data analysis provider. The actions further include applying the characteristics of the data, the analysis techniques, the requirements of the users, and the provider information, the analysis techniques, and the real-time data analysis loads to a model. The actions further include configuring the one or more particular data analysis providers to perform the analysis techniques on the data.

US Patent:

20140214643, Jul 31, 2014

Filed:

Jan 27, 2014

Appl. No.:

14/164794

Inventors:

- Jersey City NJ, US
Arun Ravindran - Del Mar CA, US
Richard Williams - Jersey City NJ, US
Cecile Levasseur - La Jolla CA, US
Jenny Guofeng Zhang - San Diego CA, US

Assignee:

OPERA SOLUTIONS, LLC - Jersey City NJ

International Classification:

G06Q 40/02

US Classification:

705 35

Abstract:

A system and method for optimizing collections processing is provided. More specifically, the system for optimizing collections processing comprises a computer system in electronic communication with an accounts database storing customer and account information therein, the computer system executing a collections processing engine, said engine performing the steps of (a) electronically receiving a notification that an account has entered a collections process, (b) defining one or more customer behavior models based on customer and account information stored in the accounts database, (c) processing the customer and account information using the one or more models to calculate one or more model scores representing a probability that the account will pay to current while in a current collections stage having a treatment action associated therewith, (d) processing the calculated one or more model scores to calculate an optimal amount of time that the account should stay in the current collections stage, (e) determining whether to transfer the account to a next collections stage having another treatment action different than the current stage, and (f) repeating steps c-e until full payment is received and removing the account from the collections process.