Portfolio

Some typical portfolios

                      Telecom

For Rogers Communications and Comcast Cable: We developed causal models of customer satisfaction; identified high-impact interventions for improving customer satisfaction; helped to develop achievable targets and strategies for improving customer experiences in different channels.

                  Energy & Utilities

We worked in partnership with North Highland consulting company to deliver a predictive model of customer bad debt and account write-offs that greatly extended the lead time over which high-risk customers could be identified and targeted for intervention.

                 Financial services

For a leading financial services company: We delivered a set of predictive clusters for simultaneously predicting churn, up-sell, and cross-sell potentials for existing customers.  The predictive validity, stability, and high practical value of the predictive clusters were confirmed by the client.

            Healthcare Insurance

For TriZetto (a health insurance back office operations Cognizant company): We assessed healthcare predictive analytics trends and vendor offerings, advised top management on predictive analytics technology acquisitions.

Legal predictive analytics: Probability of Causation (PC)

MoirAI’s technology addresses one of the main technical questions underlying countless tort litigation cases and toxic tort suits: Had a defendant taken a different level of care, or had a plaintiff’s exposure to harmful substances or conditions been less, how likely is it that the plaintiff’s injury or harm would not have occurred, or would have been less than it was?  MoirAI scientists helped pioneer the science of “probability of causation” (PC) calculations and alternatives used in worker compensation, epidemiology, and tort litigation.  Their PC calculations have been used successfully to help settle complex cases and to resolve inconclusive and costly qualitatuve legal arguments. 

For high-stakes litigation, they can be combined with toxicological and mechanistic data and epidemiological evidence to help bring clarity to framing and answering questions about how much outcome probabilities would have changed if the defendant had acted differently.  Such PC calculations, and closely related causal calculations for assigned shares in responsibility for harm with joint and several liability, go far beyond traditional epidemiological (Bradford-Hill) considerations to provide a firm scientific and conceptual basis for quantifying the effects of decisions, policies, and behaviors on outcome probabilities.