The client needed help flagging fraudulent medical insurance claims. The goal was to:
- Determine logic to flag suspicious behavior and identify providers of interest
- Leverage billing data to analyze suspicious providers
- We performed fuzzy matching to link multiple claim records to the same provider(s)
- We used geocoding to create physical distance calculations between providers and between providers and claimants
- We applied statistical methods (e.g., logistic ridge regression with sparse matrices, T-Score calculation, bootstrapping, etc.) to billing data to build propensity scoring models to rule claims as valid or invalid
- Based on our modeling results, we created the fraud flagging logic to identify suspicious behavior and providers of interest
- The team collaborated with the investigative unit, billing unit, and legal unit to create a provider fraud action plan
Fulcrum's data preparation procedures and predictive analytical models provided the quantitative basis for the provider fraud action plan.
A leading eyewear distributor was looking for analytical guidance to power their sales and marketing efforts and overcome challenges related to:
- Cross brand affinity
- Ideal price point
- Customer lifetime value
- We provided deep analysis and customer relationship management consulting using advanced data modeling and analytics
- We provided campaign management, campaign contact strategy, and campaign operations for multiple brands in the portfolio
- Our Anvil™ platform hosted the CRM database and leveraged APIs with the client and its third party data sources
Fulcrum’s advanced data modeling and technology platform enabled a data-driven end-to-end sales and marketing operation.
A leading medical insurance company was seeking data driven campaign strategy, models, and marketing operations to accelerate their acquisition efforts.
- Our Anvil™ platform securely hosted the HIPAA-compliant marketing database, and managed APIs, householding, suppressions, NCOA updates, opt-outs, etc.
- We built predictive models to improve sales and marketing targeting and efficiency, including retention models for renewals.
- Through building and implementing response, attrition, and best customer look alike models we evaluated data sources while providing cross-channel campaign solutions.
Using Fulcrum’s Anvil platform we built, hosted, and maintained a HIPAA-compliant and model-driven marketing database for cross-channel campaign solutions.
A well known weight loss service provider was seeking to:
- Deepen analytical insights for maximizing campaign effectiveness
- Analyze customer spending and attrition behavior
- Conduct campaign analysis and reporting metrics
- We developed a robust marketing database on Fulcrum’s Anvil™ platform to integrate data from multiple sources.
- We provided analytical models for customer spending, attrition, lifetime value, and segmentation to inform marketing campaigns
- We measured campaign success and refined future campaigns through a process of continuous improvement
Our team facilitated a data-driven direct-to-customer marketing operation with ongoing ROI measurement and a feedback loop of continuous improvement.
A leading blood glucose monitor manufacturer sought to:
- Modernize its communication streams
- Develop cross-channel communication coordination
- Our Anvil™ platform securely hosted the HIPAA-compliant marketing database and managed APIs.
- We built predictive models to improve customer retention and winback in the context of customer lifetime value.
- We provided ongoing cross-channel campaign experimental design and response analysis.
- We designed and carried out customer research to fine tune multi-channel communication messaging and strategy
Our data science team built comprehensive predictive models to execute upon cross-channel factors that retain customers while conducting deep market research to maximize relevant communication.
The client was seeking support in evaluating various clinical programs. Key challenges included:
- Many clinical programs were operating without a randomized control group
- Historical evaluations were done in a time consuming and ad-hoc fashion
- There was a lack of consistency in evaluation scope and methodology across different clinical programs
- All of the above made it difficult to track changes and updates
- We built matched control groups at the patient levels by matching patients enrolled in certain clinical programs with comparable patients who were not enrolled, based on a number of relevant criteria
- We calculated various outcome metrics to evaluate the program’s impact at the patient level
- The finely matched control group process allowed for result measurement by other important dimensions such as severity of illness, market, etc.
- We developed automated scripts to reduce labor hours for future updates
Fulcrum's quasi-experimental design process allowed for program result measurement where there was no hold-out control group. We also developed automated scripts to increase consistency in methodology and reduce labor hours for future program measurement.