BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
chuie
Quartz | Level 8

Any suggestion on doing "Financial impact" of predictive modeling? We have built "no show" predictive modleing for 8 clinic. We need to create a summary report in terms of revenue saved from this model.. any suggestions?

1 ACCEPTED SOLUTION

Accepted Solutions
DougWielenga
SAS Employee

The financial impact is related to what you did differently and whatever additional cost/revenue might have resulted.   Did the "no show" prediction allow you to schedule additional/alternate patients?   If you did, was there any loss due to people showing up who were not expected (e.g. extra hours worked, loss of customer satisfaction for wait time, etc...)?  There are likely a virtually limitless number of things to consider for this type of calculation so the challenge in part is to balance between the risk of oversimplifying and the risk of adding in too much complexity.  In the end, this is really a business question rather than a Data Mining problem since it depends more on the business value of making the decision and computing the resulting financial impact using those business assumptions.  This information when available can be included when building the model so that the costs and revenue from certain types of correct/incorrect decisions can influence which model is chosen but the actual valuation is purely a business decision. 

 

Hope this helps!

Doug

View solution in original post

2 REPLIES 2
DougWielenga
SAS Employee

The financial impact is related to what you did differently and whatever additional cost/revenue might have resulted.   Did the "no show" prediction allow you to schedule additional/alternate patients?   If you did, was there any loss due to people showing up who were not expected (e.g. extra hours worked, loss of customer satisfaction for wait time, etc...)?  There are likely a virtually limitless number of things to consider for this type of calculation so the challenge in part is to balance between the risk of oversimplifying and the risk of adding in too much complexity.  In the end, this is really a business question rather than a Data Mining problem since it depends more on the business value of making the decision and computing the resulting financial impact using those business assumptions.  This information when available can be included when building the model so that the costs and revenue from certain types of correct/incorrect decisions can influence which model is chosen but the actual valuation is purely a business decision. 

 

Hope this helps!

Doug

chuie
Quartz | Level 8

Thank you very much .. this is really helpful

sas-innovate-2024.png

Don't miss out on SAS Innovate - Register now for the FREE Livestream!

Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.

 

Register now!

How to choose a machine learning algorithm

Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 2 replies
  • 872 views
  • 0 likes
  • 2 in conversation