Soujanya Soni

Edge analytics as service — A service oriented framework for real time and personalised recommendation analytics

Due to the advent of technology and internet over the past few years, significant number of customers have started shopping online and accessing their bank account through various channels like Netbanking, Mobile banking etc. In this paper, we describe Edge Analytics framework which deliver analytics as a service that can be hosted by a financial institute like Bank for delivering personalized offer in real time on thier netbanking portals or on other channels. This edge analytics service can be accessed through edge APIs plugged into netbanking portals. It access the recent transactions in the log to determine offers for the customer and therefore, saving a lot of resources and effort by fetching the data from the main warehouse. Edge analytics server capability has been enhanced by incorprating knowledge such as users intent and interest from their social media profile by identifying their identity on the Online social network. This information is then feed into rule engine to generate customised offers for each user using both enterprise and social information. Edge Analytics service has been hosted on cloud which renders it scalability factor and allows different third party provders to make use of the service easily..

Towards Providing Data Validation as a Service

Data validation is one of the most important and, possibly, most under-valued task in an organization. Without clean data, an organization cannot employ sophisticated analysis and optimization tools to strive for excellence in operations, delivery or planning. Organizations have started to realize the value of data and its impact on their efficiency. Typically, they either develop in-house solutions or purchase industry standard solutions. In this work, we propose an alternative of data validation as a service offering. We argue that such a service would be a profitable proposition for both the parties, provider as well as consumer. We present a general framework to enable such an offering. We provide details on one such implementation that we carried to showcase the viability of such an approach. We propose multiple variants of the offering to handle privacy concerns of the consumer. Finally, we present a set of initial results comparing the different variants.

Data consolidation solution for internal security needs

The threats of the 21st century are too complex, difficult and time consuming to discern with traditional intelligence practices that shun advances in information technology and rely heavily on human experts. Good information is fundamental to understand and respond to 21st century national security threats. Without comprehensive information, decision-makers operate with a limited understanding of the threat horizon or the best means to address it. Required information exists across a variety of proprietary and open sources, and the volume of data available that might potentially contain relevant facts is simply too large and the bandwidth of the trained analysts is limited. Such information must be available in time-critical situations to be able to quickly connect the dots across various related pieces of information. It is imperative that decision-makers are provided intelligent tools that can automatically extract new relevant information from data without being explicitly asked, leading to actionable intelligence. To overcome these challenges we propose an information collection, management and analysis framework to meet the ever-growing threats to national security. The proposed framework establishes a collaborative environment to semi-automatically generate actionable intelligence by ensuring that the right people have access to all inclusive information at the right time. The core of this framework is to create a single view of entity by correlating information from different sources, stored in different formats. These sources can be passport, immigration, driving license, FIR records, Telecom and Utility services. The correlation algorithm is able to handle varied amount of noise in the data such as syntactic and semantic variations, format changes, spelling error, incomplete data, regional and linguistics variation as well as addition or removal of fields. The framework can further exploit the consolidated view to discover relationships between entities thus expanding the reach for relevant information. The framework provides multiple avenues of interaction and the foresight needed to incorporate new sources of data as they arise in future.

Data validation for business continuity planning

In this paper we present a system and case study for business data validation in large organizations. The validated and consistent data provides the capability to handle outages and incidents in a more principled fashion and helps in business continuity. Typically, different business units employ separate systems to produce and store their data. The data owners choose their own technology for data base storage. It is a non-trivial task to keep the data consistent across business units in the organization. This non-availability of consistent data can lead to sub optimal planning during outages and organizations can incur huge financial costs. Traditional custom data validation system fetches the data from various data sources and flow it through the central validation system resulting in huge data transfer cost. Moreover, accommodating change in business rules is laborious process. Accommodating such changes in the system can lead to re-design and re-development of the system. This is a very costly and time consuming activity. In this paper, we employ a Metadata driven rule-based data validation system, which is domain independent, distributed, scalable and can easily accommodate changes in business requirements. We have deployed our system in real life settings. We present some of the results in this paper.