Member Outreach Model to Predict Best Channel to Communicate with Members
This ML model is used to predict the best channel for reaching out to members, to ensure increased member response rate. It helps identify key attributes affecting/used for predicting the best channel for communication with the member.This model can be used for selecting the best marketing/communications channel for different use cases as well.The channels can be call,SMS and Email. It uses demographics, SDoH, clinical data and historical outreach data to determine the best channel for outreach.It is trained on a dataset contained more than 34000 members data. The performance is quit good as Accuracy is 89%,F1 score is 87% ,precision is 89% and Recall is 86%.
Input variables : Demographic, SDoH, Clinical data, Historical outreach data
Output Variables : Best Channel to communicate with member (Cold Calling/Email/SMS)
Metrics to Monitor
|
Statistical
|
:
|
Somers D |
Accuracy |
Precision and Recall |
Confusion Matrix |
F1 Score |
Roc and Auc |
Prevalence |
Detection Rate |
Balanced Accuracy |
Cohen's Kappa |
Concordance |
Gini Coefficent |
KS Statistic |
Youden's J Index
|
|
Business
|
:
|
Outreach Campaign Efficacy |
Members Engaged
|
|
Infrastructure
|
:
|
Log Bytes |
Logging/User/IAMPolicy |
Logging/User/VPN |
CPU Utilization |
Memory Usage |
Error Count |
Prediction Count |
Prediction Latencies |
Private Endpoint Prediction Latencies |
Private Endpoint Response Count
|
Visit Model :
medictiv.citiustech.com