Workforce Engagement Management

Both WFM views and Performance views utilize Analytics queries. It is difficult to configure the performance view with the filters to exactly mimic the planning groups. So, first potentially large contributor to the differences is the non symmetry between queue(s), media type(s), and skill sets between planning groups in your BU and whatever your performance view filters are set to. The source data also has to combine potentially many items and utilizes weight averaging by offered count. So, even if you could duplicate the various individual parts in a Performance view, you'd still have to do math to combine to come up with the source data view. If you feel there is an issue, then I would recommend opening a support ticket.

I would recommend automatic best method (ABM) if you want the benefit in seasonality, level shift changes, etc. You can always compare and contrast forecast accuracy/error between the two methods. ABM has shown to be much more accurate than WHI and becomes more accurate with more data.  https://help.mypurecloud.com/articles/automatic-best-method-forecast-method-overview/:

The Automatic Best Method forecasting method is the most sophisticated methodology offered in workforce management. It includes:

• Built-in, automated capabilities for historical data cleanup
• Outlier and calendar effect identification
• Pattern detection including seasonality and trends
• Best-of-best modeling to select from 20+ methodologies including ARIMA, WM, Decomp

This AI powered forecasting method creates individual forecasts with the lowest possible error using: 

• Best practices
• Outlier detection
• Mathematical fixes for missing data
• Advanced time-series forecasting techniques

------------------------------
Jay Langsford
VP, R&D
------------------------------

Hey Jay,

Thank you for your insight.

I took a look at the documentation you provided and ABM does look like it should be the best method to use as "it is much more powerful with more historical data."   However,  "this methodology looks at up to 90 days of historical data."

Jay is there any plan to have ABM look at historical data more than 90 days in the past?

For example, when forecasting the first week of the year (our busiest period for call volumes) the results we see are half of what we typically receive in calls. We have call data from January 2019 onwards.  

Is there any other tool anyone else would advise us on using that looks at the historical data that is more relevant (comparing January 2023 for predicting January 2024)

Both WFM views and Performance views utilize Analytics queries. It is difficult to configure the performance view with the filters to exactly mimic the planning groups. So, first potentially large contributor to the differences is the non symmetry between queue(s), media type(s), and skill sets between planning groups in your BU and whatever your performance view filters are set to. The source data also has to combine potentially many items and utilizes weight averaging by offered count. So, even if you could duplicate the various individual parts in a Performance view, you'd still have to do math to combine to come up with the source data view. If you feel there is an issue, then I would recommend opening a support ticket.

I would recommend automatic best method (ABM) if you want the benefit in seasonality, level shift changes, etc. You can always compare and contrast forecast accuracy/error between the two methods. ABM has shown to be much more accurate than WHI and becomes more accurate with more data.  https://help.mypurecloud.com/articles/automatic-best-method-forecast-method-overview/:

The Automatic Best Method forecasting method is the most sophisticated methodology offered in workforce management. It includes:

• Built-in, automated capabilities for historical data cleanup
• Outlier and calendar effect identification
• Pattern detection including seasonality and trends
• Best-of-best modeling to select from 20+ methodologies including ARIMA, WM, Decomp

This AI powered forecasting method creates individual forecasts with the lowest possible error using: 

• Best practices
• Outlier detection
• Mathematical fixes for missing data
• Advanced time-series forecasting techniques

------------------------------
Jay Langsford
VP, R&D