Insight, Impact, Innovation
HomeOur WorkCase StudiesAnalytics helps leading provider identify likely incremental collections from 30% of unpaid invoices

Analytics helps leading provider identify likely incremental collections from 30% of unpaid invoices

Download PDF

The Business Challenge

Escalating healthcare costs have forced employees with employer-provided insurance to bear a higher proportion of self-payment costs such as copay, coinsurance, deductible and out-of-pocket expenses. Hospitals are challenged to collect the patients’ portion of medical expenses, which according to American Hospital Association comprises 6.1% of all services. 

Multispecialty practices collect only 56.6% of their accounts receivables in the first 30 days. Many hospitals, especially a growing number of nonprofit companies are particularly vulnerable and are seeing their access to capital weakened and their capital ratings downgraded due to bad debts. 

A leading multi-billion healthcare provider system, serving 8 million patients annually, wanted to deploy analytical methods to manage and increase the collectability of the self-pay portion of services delivered.

The Solution

While maximizing point-of-service collections is a key goal, improving account receivable collections after discharge is extremely important for hospitals. Successful scoring approaches for self-pay accounts require segmenting them by understanding patients’ ability as well as their willingness to pay. 

To design a well-rounded collections strategy, it is critical to: 

  1. know which patients require assistance with payment plans, 
  2. where to apply discounts, and 
  3. define what if any additional collection resources are needed

We applied over 50 hypotheses to identify over 100 different data elements for our analysis, including patient characteristics, policy benefits, credit worthiness, and medical and procedures data to define the key drivers of patient payment behavior.

A suite of advanced predictive models was developed using machine learning techniques to gain insights into a patients’ propensity to pay, likely amount a patient will pay, and the timeframe a patient is likely to pay.

The solution helped the provider to:

  1. target the right accounts,
  2. speed collection receivables, and
  3. collect more unpaid fees

Action plan by segments

The Results

We identified five key segments with distinctive payment behaviors and recommended the following treatments:

  • Continue to bill 40% patients with little or no additional follow-ups
  • Offer payment plans and low discounts to 20% patients to collect sooner
  • Leverage collectors to target remaining segments that are highly unlikely to pay with higher discounts

The recommendations helped Provider identify segments to collect $20M in payments from unpaid health service invoices.


Providers can recover significantly higher incremental dollars by selectively offering payment plans, discounts and collection resources


More than $20 million could be collected from outstanding invoices for unpaid health services by targeting 30% of outstanding accounts


Delivered best-in-class solution of ensemble machine learning models that predict amount, time to pay, and propensity to pay