India's largest platform and marketplace for AI & Analytics leaders & professionals

Sign in

India's largest platform and marketplace for AI & Analytics leaders & professionals
Become a Thought Leader
Become a 3AI Member

Sign in

3AI Digital Library

< Go Back

Systematic targeting to shortlist customers

3AI September 10, 2020

Large player in the US healthcare industry

Problem Statement

  • Company wants to improve the completion rate by reaching out to customers more likely to complete the HRA ( for commercial plans)
  • Company does not want to invest huge sums of money on this campaign and hence wants a very precise and concise target list
  • Company expects more customers coming out of exchanges due to the implementation of the Obama Care and has no idea about the characteristics of these members

Analytics Led Approach

  • Leveraged the company’s claims data (medical claims, Rx claims, Mental Health Claims, Vision Claims), enrolment and case management data to shortlist 400+ predictors of HRA completion
  • Company did not have psychographic / behavioral data; leveraged its partnership with 3rd party vendors to arrive at 200+ behavioral predictors
  • Interactions between predictors were studied and principal components were identified.
  • Robust statistical techniques were employed to arrive at propensity rates for HRA completion based on which targets were identified.

Business Impact

  • Company was in a position to target customers for HRA completion from 10% of customer base and still increase the HRA completion rate over five fold
  • Company could compute the propensity to complete HRA at a customer level depending on behavioral parameters and change in utilization behavior

Critical Success Factors

  • partnership with 3rd party vendors enabled the clients leverage critical psychographic information that would help predict the HRA completion behavior of the members, especially for people coming off exchanges

    3AI Trending Articles

  • IIT Kanpur introduces Master’s programs in Cybersecurity

    IIT Kanpur has introduced three new cybersecurity postgraduate programs with intent to to address the need of cybersecurity personnel by ensuring training of dedicated and highly skilled manpower.   With a view to meet the shortfall in trained and skilled cybersecurity personnel in the country, the Indian Institute of Technology, Kanpur has decided to introduce […]

  • Cross-Validation techniques to assess your model’s stability

    Featured Article: Author:  Sai Nikhilesh Kasturi, Data Science & Analytics, Customer Insights & Analysis, American Airlines One of the foremost interesting and challenging things about data science hackathons in Kaggle is struggling to maintain the same ranks on both public and private leader boards. I also have been a victim in struggling to keep the […]

  • Using AI to Outwit Malicious AI

    Robust Intelligence is among a crop of companies that offer to protect clients from efforts at deception. IN SEPTEMBER 2019, the National Institute of Standards and Technology issued its first-ever warning for an attack on a commercial artificial intelligence algorithm. Security researchers had devised a way to attack a Proofpoint product that uses machine learning to identify spam emails. The system produced email headers […]

  • HCM Decision Making powered by Talent Sciences

    Talent Science is the business capability of using advanced data analysis techniques and predictive models to drive HCM decision making. It calls for a logical connection between decisions about people, HR program investments and strategic business outcomes. This can form a backbone of human resource function of all organizations independent of the sector in which it operates. […]