Causality

Understand what drives behavior and decision-making

Featured Case Study

Causality AI Informs Credit Card Collections

A U.S. financial services company showed a $5 to $7 million improvement in its credit card collections by identifying causal factors of cardholder payments.

Spotlight

THE ROLE OF EMOTION IN DECISION MAKING
Watch Video >
image of womans face looking at something
IDENTIFY RELATIONSHIPS TO ANSWER CAUSAL “WHY” QUESTIONS
Learn More >

Our Approach

Dealing with bias and causality requires a practical, proven mathematical approach. Our causality engine simplifies the process, reduces bias, and provides strategic and tactical actions that can be taken in response to change. It identifies relationships in the variables and builds a customized model. That model then refines, trains and corrects itself, providing true causal factors.

The engine discovers which variables are the best predictive drivers for the user-defined business objective from thousands of variables. In so doing, it powerfully discovers combination effects where factors that are weak predictors individually are strongly predictive in combination. This system automatically provides multiple recommendations to achieve the targeted goal.

Recent Customer Engagements

IMPROVE CREDIT CARD COLLECTIONS

A leading provider of co-branded credit cards needed help better understanding the factors involved in debt collection to reduce its high default risk, provide insights on how to improve its collections and reduce its $900 million annual write-offs. 

  • This client is expected to save $7 million per year by optimizing agent actions in its Will Pay segment.
  • We identified the 10% to 20% of account holders who are most likely to pay their bills if given a bit more time. 
  • Our solution generated data segmentation, drivers and recommendations automatically.

IDENTIFY CAUSAL BREAST CANCER GENES

A genetic diagnostic company wanted to improve its diagnostic testing and apply the most effective treatment regimen. Genetic information and historical data that followed 300 subjects over 10 years was analyzed. 

  • The solution increased predictive accuracy by 22%—from 62% to 81%.
  • It analyzed 25000 genes and identified causal gene sequences on 3 to 5 genes, rather than 70. 
  • Most importantly, it provided optimal breast cancer treatment plans for patients.

REDUCE CHURN AND BETTER UNDERSTAND YOUR CUSTOMERS

A large U.S.-based food and beverage company wanted help understanding and reducing churn worldwide. This was accomplished by identifying the drivers of churn and the data patterns it could alter to affect change.

  • The client now understands the top customers to watch in particular geographical areas.
  • It has increased its total number of customers by improving retention.

SAVE TIME, MONEY AND DECREASE PORTFOLIO RISK

An insurance company needed to reduce time and costs and improve portfolio risk. 

  • The client identified the nine variables with the best stability and relevance to predict outcomes. 
  • The solution significantly improved the speed and cost of policy issuance and reduced the costs of further tests.
  • It also maximized the number of preferred cases the client accepted for its agents and customers.

IMPROVE RESOLUTION TIME AND REDUCE COSTS

A telecommunications company needed to improve resolution time and reduce costs associated with its network operations center.

  • The client identified causal patterns and recommended solutions for each type of incident.
  • The solution suggested the top 3 results for any given problem. 
  • The result is improved productivity and a reduction in both redundancy and knowledge disparity.

Recent Customer Engagements

IMPROVE CREDIT CARD COLLECTIONS

A leading provider of co-branded credit cards needed help better understanding the factors involved in debt collection to reduce its high default risk, provide insights on how to improve its collections and reduce its $900 million annual write-offs. 

  • This client is expected to save $7 million per year by optimizing agent actions in its Will Pay segment.
  • We identified the 10% to 20% of account holders who are most likely to pay their bills if given a bit more time. 
  • Our solution generated data segmentation, drivers and recommendations automatically.

IDENTIFY CAUSAL BREAST CANCER GENES

A genetic diagnostic company wanted to improve its diagnostic testing and apply the most effective treatment regimen. Genetic information and historical data that followed 300 subjects over 10 years was analyzed. 

  • The solution increased predictive accuracy by 22%—from 62% to 81%.
  • It analyzed 25000 genes and identified causal gene sequences on 3 to 5 genes, rather than 70. 
  • Most importantly, it provided optimal breast cancer treatment plans for patients.

REDUCE CHURN AND BETTER UNDERSTAND YOUR CUSTOMERS

A large U.S.-based food and beverage company wanted help understanding and reducing churn worldwide. This was accomplished by identifying the drivers of churn and the data patterns it could alter to affect change.

  • The client now understands the top customers to watch in particular geographical areas.
  • It has increased its total number of customers by improving retention.

SAVE TIME, MONEY AND DECREASE PORTFOLIO RISK

An insurance company needed to reduce time and costs and improve portfolio risk. 

  • The client identified the nine variables with the best stability and relevance to predict outcomes. 
  • The solution significantly improved the speed and cost of policy issuance and reduced the costs of further tests.
  • It also maximized the number of preferred cases the client accepted for its agents and customers.

IMPROVE RESOLUTION TIME AND REDUCE COSTS

A telecommunications company needed to improve resolution time and reduce costs associated with its network operations center.

  • The client identified causal patterns and recommended solutions for each type of incident.
  • The solution suggested the top 3 results for any given problem. 
  • The result is improved productivity and a reduction in both redundancy and knowledge disparity.

Take the first step

Contact us for more information