Exploring new concepts with outlier data marts
This model is now being used to automate and generate data marts for clients to help identify inaccuracies and errors, thereby improving savings.
EXL Health theorized that data marts could identify claims that fall outside typical parameters. By flagging and reviewing these outliers, inaccuracies and errors could potentially be identified.
Within one month, EXL Health built a data mart that identified claim overpayments. This model is now being used to automate and generate data marts for clients to help identify inaccuracies and errors, thereby improving savings.
- Created new methods for identifying outliers and inaccuracies in data marts
- Built a data mart leveraging this methodology to identify claim overpayments within one month
- Data mart now being deployed for clients