The Fifth Elephant winter edition 2019

Winter edition of India's most renowned conference on big data and data science

Tackling fraud in Fin-tech space

Submitted by Raj Vardhan Singh (@is-rajvardhan) on Wednesday, 29 August 2018

videocam_off

Technical level

Intermediate

Section

Full talk

Status

Submitted

Vote on this proposal

Login to vote

Total votes:  0

Abstract

Fraud as we know it has existed in some or the other form since the concept of monetary transactions came into existence. As part of this session, we would discuss about classifying frauds into different categories and mechanisms to tackle them using behavioral science, honeypots & various other methods in a man-machine ecosystem.

Outline

  1. Introduction to Fraud
    a. A brief history on fraud

    b. Differentiating Fraud from the noise

    c. Various examples of fraud that we see

  2. Detecting Fraud
    a. Detecting Identity Fraud

    b. Detecting Behavioural Fraud

    c. Detecting Opportunism

  3. Designing products to add better signals for classifications

  4. Actions post detecting a suspicious behavior

Speaker bio

Raj Vardhan has about 7 years of experience working with Fortune 100 companies as well startups across the globe consulting on data, tech and product. He is currently the lead data scientist and head of analytics & Inferences at Simpl. In addition, he also looks into the consumer facing part of the product along-with consumer centric risk. In his last 3 + years at Simpl, he has been involved in building the underwriting models, fraud detection mechanisms and the in-house ML platform for at-scale training and deployment of models.

His major interest lies in working with businesses on Data Science Adoption, behavioral sciences and designing intelligent product flows.

Comments

  • 1
    Zainab Bawa (@zainabbawa) Reviewer 2 months ago

    Raj, share draft slides and preview video by 5 October to complete evaluation of your proposal.

Login with Twitter or Google to leave a comment