The Boston Consulting Group, Inc.

Accenture Global Solutions Limited

Arun Karthik Ravindran

Vincent Francois Faber

Jack Chua

Sudhir Ranganna Patavardhan

Anu Tayal

Lisa X Wilson

Muhammad Arjumand Masood

Naga Viswanath

Victor Kostyuk

Methods and systems for predicting are disclosed. Records for transactions can be stored, each record comprising an indication identifying items involved in a transaction and an indication of a time elapsed between the transaction and a previous transaction. The records for transactions can be analyzed to produce a probability that the items will be involved in a next transaction.

Methods and systems for analyzing and predicting transactions

Methods and systems for using reinforcement learning to optimize promotions are disclosed. A promotion can be offered to a customer computing device, using a reinforcement learning model with a sensitivity parameter. A customer's reaction to the promotion can be observed.

Systems and methods of deploying reinforcement learning

Methods and Systems for using reinforcement learning to optimize promotions. A promotion can be offered to a customer for a prepaid calling card using a reinforcement learning model with a sensitivity parameter. The reinforcement learning model can estimate a time period during which the customer will purchase the prepaid calling card. The customer's reaction to the promotion can be observed. A reward or a penalty can be collected based on the customer's reaction. The reinforcement learning model can be adapted based on the reward or the penalty to optimize the timing of the promotion by estimating a new time period during which the customer will purchase the prepaid calling card. The reward proxy and/or the penalty proxy can comprise frequency of usage.

Methods and systems for using reinforcement learning

Methods and systems for using reinforcement learning to optimizing promotions. A promotion for a product and/or service is offered to a customer using a reinforcement learning model. The customer's reaction is observed. A reward or a penalty is collected based on the customer's reaction. The reinforcement learning model is adapted based on the reward or penalty.

Systems and methods of using reinforcement learning for promotions

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.

Engineering data analytics platforms using machine learning

Systems and methods for predicting are described herein. A record for each of a plurality of events associated with user transactions can be stored. A sequential plurality of the events can be analyzed using a unidirectional long short term memory (LSTM) and first and second dense neural network layers configured to receive output from the LSTM network.

Systems and methods for learning and predicting transactions

Systems and methods for predicting transactions. A record is stored for each of a plurality of transactions, each record comprising an indication identifying each item from a set of items involved in the transaction and an indication of a time elapsed between the transaction and a previous transaction. A sequential plurality of the transactions is analyzed using a unidirectional long short term memory (LSTM) network to produce a probability that each item from the set of items will be involved in a next transaction, and a time estimate value for a future time when the next transaction will occur. The probability for each item and the time estimate value is stored in the memory as a prediction.

Growing community of inventors

Somerville, MA, United States of America

Arun Karthik Ravindran