Sameep Mehta

Bio: Sameep Mehta is an academic researcher from IBM. The author has contributed to research in topics: Service (business) & Resource (project management). The author has an hindex of 22, co-authored 160 publications receiving 2093 citations. Previous affiliations of Sameep Mehta include Lady Hardinge Medical College & All India Institute of Medical Sciences.

Information integration for movies data using graph database

Abstract: The development of the Internet in the recent years has made it possible to access different information systems anywhere in the world. Information Integration is the merging of information from heterogeneous sources with differing conceptual, contextual and typographical representations. In this paper, we exploit Information Integration techniques for movies data from different sources over the web. Graphs are used to model many complex data objects and their relationships in the real world. In recent years, graphs have become increasingly popular in a variety of domains varying from Biology, Chemistry, Healthcare systems and computer vision to Business Intelligence and Social Media Analytics. We have developed a system that integrates data about movies from various sources across the web and populated the TITAN graph database. This enables us to show that complex information can be retreived using simple queries using Gremlin, a graph query language.

Containment Policies for Transmissible Diseases

Abstract: 1. ABSTRACT Till date, there have been several cases of H5N1 inuenza virus outbreak in avian populations. It is speculated that the mutations in highly unstable inuenza virus represents a serious transmissible pandemic threat. Therefore, it is essential to be prepared for such a sudden and fatal transmissible disease outbreak. In this paper, we propose several strategies to curb such transmissible diseases from spreading. Our policies identies individuals and locations which play a vital role in spreading the disease. Our analysis is based on simulation data generated by Episims system. We model this data as People-People Contact Network and PeopleLocations Activity Graph. We also evaluate our proposed strategies under two practical constraints viz. limited number of anti-viral drugs and the delay in implementation of containment policies.

RETRAiN: a REcommendation tool for reconfiguration of retail bank branch

Abstract: Customers in many developing regions (like India) use physical bank branch as primary and preferred banking channel, resulting in high footfall in the branch. This results in high wait time of customers and high pressure on organization's resources, impacting customer satisfaction (CSAT) as well as employee satisfaction (ESAT) adversely. A naive solution to handle this is to increase the service personnel to cater to the customers. However, this is an unviable alternative because this impacts top and bottom line of the bank. Therefore, organizations are strategically looking for intelligent systems which can help in fine tuning the overall business process to maximize their business objectives while incurring zero or very less investments. Towards this end, we present a system RETRAiN to enable such calibration of various components of bank operations. Based on real time data like waiting customers, service requests, availability of service personnel and business metrics, the system provides recommendations for reconfiguration of the operations. The reconfiguration includes selection of scheduling policy, number of service personnel and configuration of service personnel. We present the overall system along with analysis and optimization algorithms for generating the recommendations. To showcase the efficacy and usefulness of our system, we present results based on data collected over a period of four months from multiple branches of a leading bank in India.

System and method for root cause analysis in large scale data curation flows using provenance

Abstract: Methods, systems and computer program products for root cause analysis using provenance data are provided herein. A computer-implemented method comprises computing a plurality of provenance paths for at least one of a plurality of data elements in a curation flow and a plurality of groups of data elements in the curation flow, analyzing the computed provenance paths to determine one or more errors in the curation flow, and outputting the one or more errors in the curation flow to at least one user. The analyzing comprises at least one of identifying which of the computed provenance paths are partial provenance paths, and identifying one or more output records associated with the curation flow, wherein the one or more output records comprise incorrectly curated data, and identifying the computed provenance paths that respectively correspond to the one or more output records comprising the incorrectly curated data.

Modeling the temporal behavior of clients to develop a predictive system

Abstract: A method, system and computer program product are disclosed for modeling the temporal behavior of clients to develop a predictive system to influence client relationships. In an embodiment, the method comprises establishing for each of a plurality of clients a temporal model for a given time period, and the temporal model identifies a plurality of factors as contributing to a specified relationship with the each client over the given time period. For each of a plurality of different stages of the given time period, the temporal model identifies one or more of these factors as contributing to the specified relationship with the each client. One of the clients is identified as a model client for another client, and the temporal model of this model client is used to predict one or more of the plurality of factors as contributing to a specified relationship with this another client at a specified time.

The spread of true and false news online

Abstract: We investigated the differential diffusion of all of the verified true and false news stories distributed on Twitter from 2006 to 2017. The data comprise ~126,000 stories tweeted by ~3 million people more than 4.5 million times. We classified news as true or false using information from six independent fact-checking organizations that exhibited 95 to 98% agreement on the classifications. Falsehood diffused significantly farther, faster, deeper, and more broadly than the truth in all categories of information, and the effects were more pronounced for false political news than for false news about terrorism, natural disasters, science, urban legends, or financial information. We found that false news was more novel than true news, which suggests that people were more likely to share novel information. Whereas false stories inspired fear, disgust, and surprise in replies, true stories inspired anticipation, sadness, joy, and trust. Contrary to conventional wisdom, robots accelerated the spread of true and false news at the same rate, implying that false news spreads more than the truth because humans, not robots, are more likely to spread it.

Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification

Abstract: The paper “Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification” by Joy Buolamwini and Timnit Gebru, that will be presented at the Conference on Fairness, Accountability, and Transparency (FAT*) in February 2018, evaluates three commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition. The study finds these services to have recognition capabilities that are not balanced over genders and skin tones [1]. In particular, the authors show that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men.

A Survey on Bias and Fairness in Machine Learning

Abstract: With the widespread use of AI systems and applications in our everyday lives, it is important to take fairness issues into consideration while designing and engineering these types of systems. Such systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that the decisions do not reflect discriminatory behavior toward certain groups or populations. We have recently seen work in machine learning, natural language processing, and deep learning that addresses such challenges in different subdomains. With the commercialization of these systems, researchers are becoming aware of the biases that these applications can contain and have attempted to address them. In this survey we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined in order to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and how they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.