Control group configuration for predictions
Valid from Pega Version 8.5
You can now configure a control group for your predictions in Prediction Studio. Based on the control group, Prediction Studio calculates a lift score for each prediction that you can later use to monitor the success rate of your predictions.
For more information, see Customizing predictions.
Response timeout configuration for predictions
Valid from Pega Version 8.5
You can now set a response timeout for your predictions in Prediction Studio. By setting a response timeout, you control how Prediction Studio registers customer responses that later serve as feedback data for your predictions.
For more information, see Customizing predictions.
Rule creation and simulations of changes in a change request in the Decision Manager portal
Valid from Pega Version 7.2.2
Two major enhancements to revision management give Decision Manager portal users more control over change requests. Revision managers and strategy designers can now create rule instances as part of a regular change request. They also can run data flows to do simulations of changes that are introduced by the change request.
For more information, see Rule creation and simulations of changes in a change request in the Decision Manager portal.
Language detection option in Text Analyzer
Valid from Pega Version 7.2.2
On the Text Analyzer form, you can identify the language of incoming records based on their language metadata tag by selecting the Language detected by publisher option. This option applies only to Text Analyzer rules that process Twitter records. By combining this option with the advanced language filtering criteria of Twitter data sets, you can filter out unnecessary data and analyze only the Twitter records that are relevant to your business objective.
For more information, see Configuring advanced filter conditions for Twitter data and Configuring language settings.
Options for filtering data in Twitter data sets
Valid from Pega Version 7.2.2
Twitter data sets have more options for filtering tweets. On the Advanced options tab of the Edit Data Set form, you can configure your Twitter data set to not analyze tweets if they contain specific keywords or if the tweets are made by specific authors. You can also select the languages to analyze based on the language metadata tag of the incoming tweets (tweets in other languages are ignored). By configuring the filtering criteria, you can ignore data that is not relevant to your text analysis and retrieve only the records that you need.
For more information, see Configuring advanced filter conditions for Twitter data.