scispace - formally typeset
Search or ask a question
Author

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.


Papers
More filters
Proceedings Article
01 Jan 2009
TL;DR: Analysis of interaction networks extracted from the service operations is the focus of this tutorial and it is important to derive information on effectiveness of the interactions and the process of effective team formations.
Abstract: One of the distinguishing features of the service sector is high emphasis on people interacting with people and serving the customer rather than transforming physical goods in the process. In traditional manufacturing, the machines are characterized by their ability to do only prespecified set of tasks, with quantifiable and predictable productivity rates. These properties makes it is relatively easy to understand, model and analyze the interactions e.g. One machine of type X can process the output of three machines of type Y. However, People, the analogue of machines in service chains are characterized by, (i) unpredictable productivity rate (ii) ability to become proficient and diversified in skill-set with time. Hence, people to people interaction which is pervasive in services industry provides technical challenges from analysis, diagnostic and optimization purposes. It is evident that analysis of such interactions is an essential aspect of designing effective and efficient services delivery. The results of analysis can be used to handle various aspects, e.g., training, team building, risk management etc. Analysis of interaction networks extracted from the service operations is the focus of this tutorial. In many ways, interaction networks are similar to the well-studied social networks. Traditionally, social network analysis has been used to study structural properties of the networks and the positional properties of the individuals. However, from the perspective of interaction networks, it is important to derive information on effectiveness of the interactions and the process of effective team formations. When these objective are taken into account, a rich set of problems emerge, some of which are further generalizations of traditional analysis. Typically, solving these problems involves multidisciplinary approach as in understanding the constraints of the domain, import of mathematical analysis techniques and appropriate interpretation of the results.

1 citations

Patent
22 Aug 2019
TL;DR: In this paper, the authors propose a method to assign a machine learning model signature to a model using data points and corresponding data labels from training data, and classify the model as a stolen classifier based on a predetermined threshold.
Abstract: One embodiment provides a method, including: assigning a machine learning model signature to a machine learning model, wherein the machine learning model signature is generated using (i) data points and (ii) corresponding data labels from training data; receiving input comprising identification of a target machine learning model; acquiring a target signature for the target machine learning model by generating a signature for the target machine learning model using (i) data points from the assigned machine learning model signature and (ii) labels assigned to those data points by the target machine learning model; determining a stolen score by comparing the target signature to the machine learning model signature and identifying the number of data labels that match between the target signature and the machine learning model signature; and classifying the target machine learning model as stolen based upon the stolen score reaching a predetermined threshold.

1 citations

Proceedings ArticleDOI
08 Jul 2012
TL;DR: A Metadata driven rule-based data validation system, which is domain independent, distributed, scalable and can easily accommodate changes in business requirements is employed.
Abstract: 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.

1 citations

Proceedings ArticleDOI
Ashima Suvarna, Kuntal Dey1, Seema Nagar1, Nishtha Madaan1, Sameep Mehta1 
01 Nov 2019
TL;DR: This work is the first of its kind, that establishes a baseline for enhancing the cross-gender acceptability of product descriptions, and proposes a framework for e-retailers to provide such gender-neutral product descriptions.
Abstract: Fair computing has emerged as a key area of artificial intelligence (AI), and especially machine learning (ML). Identification and mitigation of several types of biases, spanning over data and machine learning models, has attracted both research and regulatory attention. In this work, we explore the presence and degree of gender bias in product descriptions featured on e-commerce websites. Using the knowledge obtained in analysis, we recommend methods to debias the product description, using a product feature level text selection scheme, sourced by customer reviews. Our work is the first of its kind, that establishes a baseline for enhancing the cross-gender acceptability of product descriptions, and proposes a framework for e-retailers to provide such gender-neutral product descriptions.

1 citations

Proceedings Article
07 Aug 2011
TL;DR: These efforts towards design and analysis of value creation networks are summarized: 1) network representation of interactions and value creations, 2) identify contribution of a node based on values created from various activities, and 3) ranking nodes based on structural properties of interaction and the resulting values.
Abstract: There are many diverse domains like academic collaboration, service industry, and movies, where a group of agents are involved in a set of activities through interactions or collaborations to create value. The end result of the value creation process is two pronged: firstly, there is a cumulative value created due to the interactions and secondly, a network that captures the pattern of historical interactions between the agents. In this paper we summarize our efforts towards design and analysis of value creation networks: 1) network representation of interactions and value creations, 2) identify contribution of a node based on values created from various activities, and 3) ranking nodes based on structural properties of interactions and the resulting values. To highlight the efficacy of our proposed algorithms, we present results on IMDB and services industry data.

1 citations


Cited by
More filters
Journal ArticleDOI
09 Mar 2018-Science
TL;DR: A large-scale analysis of tweets reveals that false rumors spread further and faster than the truth, and false news was more novel than true news, which suggests that people were more likely to share novel information.
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.

4,241 citations

01 Jan 2012

3,692 citations

21 Jan 2018
TL;DR: It is shown that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men, in commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition.
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.

2,528 citations

Posted Content
TL;DR: This survey investigated different real-world applications that have shown biases in various ways, and created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems.
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.

1,571 citations