![](https://higherlogicdownload.s3.amazonaws.com/GENESYS/MessageImages/4c93ecddb65641a7b19cff99aca9cbd8.png)
Hey fellow WEMers,
Hello from Xperience in Denver – are you here, find the WEM Knowledge Hub Booth and say hi 😊
Following on from our AI in Speech and Text Analytics last week, did you know there are lot of features that use AI in Resource Management!
These include:
- Automatic Best Method Forecasting
And not only that - check out what is also on the Roadmap 🙌🙌🙌🙌
Here we go again! To put a bit more context into these and what they are, let me try to explain in my own way😉
Firstly, lets cover Forecasting in Genesys Cloud - what does it do?
It provides forecasters with a continuous and accurate AI/Machine Learning powered prediction of the future, with the ability to perform what-if analysis and create permanent overrides, so that workforce planners can effectively schedule into the future as business demands change.
AI Forecasting in Genesys Cloud
![](https://higherlogicdownload.s3.amazonaws.com/GENESYS/MessageImages/4b2dbc42642a48ec962603d14011908a.png)
Artificial Intelligence in the forecast generation process provides extremely fast results.
• The average total processing time is around 10 seconds, with a maximum of 20 seconds.
• Total processing time is the time that each request waits in queue and the time it takes to process the request.
• Genesys Cloud batch processes all the optimal models nightly using an extensive set of historical data and chooses the best forecast using AI; when a forecast request is made to Genesys, the model and optimal parameters are already available.
• As your history changes and updates, the AI will make modifications to the variables and parameters and will provide the best model as time goes on.
• Complexity may exist when a Planning Group definition changes during the day, where there is a need to recreate and re-optimize models, in which case it could take up to 150 seconds to complete the transaction.
![](https://higherlogicdownload.s3.amazonaws.com/GENESYS/MessageImages/262d88fb457a45beaf9c40139353bbe3.png)
What are the Core Capabilities of Forecasting with Artificial Intelligence
• Completely automates the Forecast Process.
• Automatic Detection of Time Series Events
• Missing Data
• Operating Hours
• Leading or Trailing Zeroes
• Outliers and Anomaly detection
• Special Event Detection and Calendar day impacts.
• 27 individual Algorithms, 1000's of configurations
• Average Forecast generates 200,000 iterations per model.
• Automatically chooses most accurate model.
This enables Forecasters to make informed decisions such as:
• Filtering
• Metric filtering.
• Planning group filtering.
• Select 1/3/5-day period view.
• Weekly and Daily view.
• Charts
• Easily see the forecast in a chart.
• Drill into a specific date or time range.
• Adjust values directly in the chart.
• See your forecast vs actuals.
• Historic Overlays
• Easily view the forecast for days in the past.
• Easily add modifications to the forecast being viewed.
• Applies to various metric types.
• Auditing
• View who imported or made changes to a forecast.
What is Automatic Best Method Forecasting?
![](https://higherlogicdownload.s3.amazonaws.com/GENESYS/MessageImages/fbe8da25477f498baac6351f0e27e8b4.png)
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
Ensemble forecasting
Ensemble is a post processing activity that evaluates multiple forecasting models to create “one” forecast.
- By combining various models, we increase the overall accuracy of the forecast.
- This helps avoid any situations where a peak or valley can be overvalued by one model.
- Combines different forecasting models.
• Arima
• Holt Winters
• Random Walk
• And More
Well, I do hope that gives you an insight of what we have now for Resource Management – isn’t AI great??
Oh yes, it is, here's a little more about what’s on the roadmap…….
Continuous Forecasting – will provide forecasters with a live two-year forecast in a new UI that updates nightly.
Again, I am not party to too much more info than this but keep an eye out for more information as we learn more here on the WEM Community!
#Forecasting
------------------------------
Tracy
Genesys
------------------------------