Abstract: Disclosed is method and system for generating recommendations to a user. System receives real time data associated with users for scenarios and batch data associated with multiple users from different data sources, received from different data channels. The user is online user. System pre-processes batch data and real time data to generate pre-processed data and stores preprocessed data in distributed, scalable big data store. System filters pre-processed data based on rules to obtain filtered data. System applies combination of machine learning techniques on filtered data, based on the scenarios associated with the user, leveraging inter-play between machine learning techniques, to generate personalized recommendations for individual user and storing the personalized recommendations in distributed database. Machine learning techniques are customized to work in distributed processing mode to reduce overall processing time.

Abstract: This disclosure relates to modeling an Agile team structure such that it aligns with Agile principles, achieve synergy and deliver intended business benefits. Current approach to modelling depends on unproven manually arrived patterns that do not predict benefits, are based on limited number of experts utilizing heuristics from personal experience. Once a working model is derived, it is refined over time which is a slow process with no verification of its effectiveness. In accordance with the present disclosure, scalable and customizable location independent Agile delivery models can be generated using a palette based user interface such that constraints are optimized. A pre-configured meta-model is chosen and the location independent model is generated given the constraints. A compliance indicator provides a degree of compliance with the Agile principles. The model is then evaluated using machine learning models that have been trained by leveraging a knowledge base of successfully implemented Agile models.

Abstract: This disclosure relates to modeling an Agile team structure such that it aligns with Agile principles, achieve synergy and deliver intended business benefits. Current approach to modelling depends on unproven manually arrived patterns that do not predict benefits, are based on limited number of experts utilizing heuristics from personal experience. Once a working model is derived, it is refined over time which is a slow process with no verification of its effectiveness. In accordance with the present disclosure, scalable and customizable location independent Agile delivery models can be generated using a palette based user interface such that constraints are optimized. A pre-configured meta-model is chosen and the location independent model is generated given the constraints. A compliance indicator provides a degree of compliance with the Agile principles. The model is then evaluated using machine learning models that have been trained by leveraging a knowledge base of successfully implemented Agile models.

Abstract: The disclosure relates generally to managing data of a customer in a distributed computing environment and more particularly to a system and a method for implementing retail customer analytics data model in a distributed computing environment. Customer data, transaction data, and interaction data of a customer in a form of facts and dimensions is received from a plurality of sources. A relationship in the customer data is identified by checking the facts and the dimensions in the plurality of sources. Based on the relationship, a unified customer profile is created. Further, a customer identity is generated by performing an identity matching on the unified customer profile. The transaction data received from the plurality of sources is merged to create a unified transaction model. Subsequently, the customer identity is linked with the unified transaction model and the interaction data to generate a plurality of customer analytics records.

Abstract: Disclosed is method and system for generating recommendations to a user. System receives real time data associated with users for scenarios and batch data associated with multiple users from different data sources, received from different data channels. The user is online user. System pre-processes batch data and real time data to generate pre-processed data and stores preprocessed data in distributed, scalable big data store. System filters pre-processed data based on rules to obtain filtered data. System applies combination of machine learning techniques on filtered data, based on the scenarios associated with the user, leveraging inter-play between machine learning techniques, to generate personalized recommendations for individual user and storing the personalized recommendations in distributed database. Machine learning techniques are customized to work in distributed processing mode to reduce overall processing time.

Abstract: The disclosure relates generally to managing data of a customer in a distributed computing environment and more particularly to a system and a method for implementing retail customer analytics data model in a distributed computing environment. Customer data, transaction data, and interaction data of a customer in a form of facts and dimensions is received from a plurality of sources. A relationship in the customer data is identified by checking the facts and the dimensions in the plurality of sources. Based on the relationship, a unified customer profile is created. Further, a customer identity is generated by performing an identity matching on the unified customer profile. The transaction data received from the plurality of sources is merged to create a unified transaction model. Subsequently, the customer identity is linked with the unified transaction model and the interaction data to generate a plurality of customer analytics records.