Karthik Balakrishnan, Ph.D.

Karthik Balakrishnan, Ph.D.

Southlake, Texas, United States
4K followers 500+ connections

Join to view profile

About

Visionary senior executive with a PhD in Artificial Intelligence and 25+ years of…

Activity

Join now to see all activity

Experience

  • Cover Whale Graphic

    Cover Whale

    New York City Metropolitan Area

  • -

    Des Moines Metropolitan Area

  • -

    Lehi, Utah, United States

  • -

    Lehi, UT

  • -

    Greater Salt Lake City Area

  • -

  • -

  • -

  • -

  • -

  • -

  • -

Education

Volunteer Experience

Publications

  • Verisk Health's Fraud Alliance - The Power of Pooled Data

    Can a family practitioner actually render 50 hours of service each day? Well, yes and no. Obviously, no individual can achieve that feat, yet one provider divided that many hours among several health plans — unbeknownst to each of them. In an industry facing new scams and trends in fraud, here's news about an alliance aimed at pooling healthcare data across multiple payers to prevent schemers from being able to divide and conquer.

    See publication

  • Text Mining in the P&C Back Office

    Property Casualty 360

    Other authors
    See publication

  • Innovations in Claim Fraud Detection

    Property Casualty 360

    Despite years of ongoing efforts to identify and curb insurance fraud, it remains a significant problem. Conservative estimates from the Insurance Information Institute (I.I.I.) place the figure for annual P&C payouts on fraudulent or padded claims at more than $30 billion. A further disturbing statistic suggests that 10 percent of losses and loss adjustment expenses (LAE) are associated with fraud and abuse. Thus, a carrier with $100 million in direct written premium (DWP) and running at a…

    Despite years of ongoing efforts to identify and curb insurance fraud, it remains a significant problem. Conservative estimates from the Insurance Information Institute (I.I.I.) place the figure for annual P&C payouts on fraudulent or padded claims at more than $30 billion. A further disturbing statistic suggests that 10 percent of losses and loss adjustment expenses (LAE) are associated with fraud and abuse. Thus, a carrier with $100 million in direct written premium (DWP) and running at a 70-percent combined ratio is likely leaking more than $7 million annually because of fraudulent claim activities.

    Other authors
    See publication

  • Leveraging Text Mining in Insurance

    Insurance & Technology

    It is commonly believed that more than 90 percent of any organization's information is buried in unstructured data, such as text (documents, reports, notes) and pictures. This is particularly true in the property/casualty insurance industry, where unstructured data in the form of paper files, faxes, documents, adjuster notes, and underwriter comments abound. Recent advances in text mining technologies have made it possible to harvest valuable information buried in such unstructured data and…

    It is commonly believed that more than 90 percent of any organization's information is buried in unstructured data, such as text (documents, reports, notes) and pictures. This is particularly true in the property/casualty insurance industry, where unstructured data in the form of paper files, faxes, documents, adjuster notes, and underwriter comments abound. Recent advances in text mining technologies have made it possible to harvest valuable information buried in such unstructured data and leverage it for business results.

    See publication

  • Applying Advanced Analytics to Marketing Strategies

    ISO Review

    See publication

  • Advances in the Evolutionary Synthesis of Intelligent Agents

    MIT Press

    Other authors
    See publication

  • Evolutionary and Neural Synthesis of Intelligent Agents

    Advances in the Evolutionary Synthesis of Intelligent Agents

    Other authors
    See publication

  • Evolving Neuro-Controllers and Sensors for Artificial Agents

    Advances in the Evolutionary Synthesis of Intelligent Agents

    Other authors
    See publication

  • Spatial Learning and Localization in Rodents: A Computational Model of the Hippocampus and Its Implications for Mobile Robots

    Adaptive Behavior

    The ability to acquire a representation of the spatial environment and the ability to localize within it are essential for successful navigation in a-priori unknown environments. The hippocampal forma tion is believed to play a key role in spatial learning and localization in animals in general and rodents in particular. This paper briefly reviews the relevant neurobiological and cognitive data, and their relation to computational models of spatial learning and localization used in contempo…

    The ability to acquire a representation of the spatial environment and the ability to localize within it are essential for successful navigation in a-priori unknown environments. The hippocampal forma tion is believed to play a key role in spatial learning and localization in animals in general and rodents in particular. This paper briefly reviews the relevant neurobiological and cognitive data, and their relation to computational models of spatial learning and localization used in contempo rary mobile robots. It proposes a hippocampal model of spatial learning and localization, and characterizes it using a Kalman filter based tool for information fusion from multiple uncertain sources. The resulting model not only explains neurobiological and behavioral data from rodent experiments, but also allows a robot to learn a place-based metric representation of space and to localize itself in a stochastically optimal manner. The paper presents an algorithmic implementa tion of the model and results of several experiments that demonstrate its capabilities. These include the ability to disambiguate perceptually similar places, scale well with increasing errors, and the automatic acquisition of spatial information at multiple resolutions.

    Other authors
    See publication

  • Improving Convergence of Back-Propagation by Handling Flat-Spots in the Output Layer

    International Conference of Artificial Neural Networks (ICANN'92)

    Back-propagation (BP) is one of the most widely used procedures for training
    multi-layer arti cial neural networks with sigmoid units. Though successful in a number
    of applications, its convergence to a set of desired weights can be excruciatingly slow.
    Several modi cations have been proposed for improving the learning speed.
    The phenomenon of flat-spots is known to play a significant role in the slow convergence
    of BP. The formulation of the BP Learning rule prevents the network…

    Back-propagation (BP) is one of the most widely used procedures for training
    multi-layer arti cial neural networks with sigmoid units. Though successful in a number
    of applications, its convergence to a set of desired weights can be excruciatingly slow.
    Several modi cations have been proposed for improving the learning speed.
    The phenomenon of flat-spots is known to play a significant role in the slow convergence
    of BP. The formulation of the BP Learning rule prevents the network from learning
    effectively in the presence of flat-spots. In this paper we propose a new approach to
    minimize the error such that flat-spots occurring in the output layer are appropriately
    handled, thereby permitting the network to learn even in the presence of flat-spots.
    The improvement provided by the technique is demonstrated on a number of standard
    benchmark data-sets. More importantly, the speedup in learning is obtained with little
    or no increase in the computational requirements of each iteration.

    Other authors
    See publication
Join now to see all publications

Honors & Awards

  • Verisk Leadership Excellence Program - Harvard Business School

    Harvard Business School

    Chosen to participate in a customized Executive program for select Verisk senior leaders delivered by Harvard Business School and UVA Darden

  • Quoted in Article by Claims Canada

    Claims Canada

    Harris, Craig. "Capitalizing on Claims Data." Claims Canada. June 1, 2015. http://www.claimscanada.ca/capitalizing-on-claims-data/

  • Quoted in Article by Reuters

    Reuters

    Begley, Sharon and M. B. Pell. "Factbox: Using the Data on Medicare's Payments to Doctors." Reuters. April 9, 2014. http://reut.rs/1qjgUWH

  • Quoted in Article by Modern Healthcare

    Modern Healthcare

    Conn, Joseph. "Humana, Centene to target fraudsters by pooling data with analytics firm." Modern Healthcare. August 22, 2013.
    http://www.modernhealthcare.com/article/20130822/NEWS/308229953

  • Interviewed for an Article by Insurance Networking News

    Insurance Networking News

    McMahon, Chris. "Text Mining for Deeper Understanding." Insurance Networking News. May 31, 2012.
    http://www.insurancenetworking.com/issues/2008_83/data-analytics/verisk-analytics-text-mining-30476-1.html

  • Center of Best Practice for Customer Analytics

    Allianz

    Chosen to represent Fireman's Fund at Allianz' Customer Analytics summit in Munich and broadly recognized as the leading practice for customer analytics by other operating entities

  • Cutting Edge Research Award

    Allstate

    Chairman's research award for developing a fraud detection solution an an ensemble of a series of underlying machine learning and statistical models

  • Research Excellence Award

    Iowa State University

    Recognition of research embodied in my PhD dissertation. <5% of PhD dissertations at Iowa State University receive this award.

  • Teaching Excellence Award

    Iowa State University

    Recognized for excellence as a teaching assistant in senior undergraduate and graduate level courses

Languages

  • English

    Native or bilingual proficiency

  • Hindi

    Native or bilingual proficiency

  • Tamil

    Native or bilingual proficiency

Recommendations received

26 people have recommended Karthik

Join now to view

More activity by Karthik

View Karthik’s full profile

  • See who you know in common
  • Get introduced
  • Contact Karthik directly
Join to view full profile

Other similar profiles

Explore more posts

Explore top content on LinkedIn

Find curated posts and insights for relevant topics all in one place.

View top content

Add new skills with these courses

See all courses