Intelligent transaction scoring
Systems and methods provide a flexible environment for intelligently scoring transactions from data sources. An example method includes providing a user interface configured to generate a rubric by receiving selection of one or more one or more conditions, each condition identifying a tag generated by a classifier in the library of classifiers and for each identified tag, receiving selection of a value for the tag that satisfies the condition and receiving selection of an outcome attribute for the condition. The outcome attribute may be a weight for the tag or an alert condition. The method includes storing the rubric in a data store and applying the stored rubric to scoring units of a transaction. The method also includes aggregating scores for transactions occurring during a trend period and displaying the trend score. In some implementations, at least one classifier in the library is a rule-based classifier defined by a user.
1 . A method comprising:
generate tags for each transaction in a plurality of transactions by applying classifiers in a library of classifiers to the plurality of transactions, each transaction representing a conversation organized into scoring units;
calculating a respective transaction score for each transaction of the plurality of transactions based on the tags and on scoring criteria that apply to the transaction;
identifying a set of transactions of the plurality of transactions that meet an alert condition based on the respective transaction scores or the tags; and
generating a user interface configured to:
display a respective identifier for each transaction in the set of transactions,
display a respective snippet for each transaction in the set of transactions, and
display, for each transaction in the set of transactions, tags generated for the transaction.
2 . The method of claim 1 , wherein calculating the respective transaction score for a transaction includes:
for each scoring unit of the transaction, applying the classifiers to the scoring unit, wherein applying the classifiers labels the scoring unit with tags;
aggregating the tags of the scoring unit to generate transaction level tags; and
calculating the transaction score based on the transaction level tags and the scoring criteria.
3 . The method of claim 1 , wherein each classifier is associated with a different tag.
4 . The method of claim 1 , wherein at least one classifier is a rule-based classifier defined by a user.
5 . The method of claim 4 , wherein the rule-based classifier includes a tag defined by the user and includes a particular condition, the rule-based classifier being configured to test for presence or absence of the particular condition in a transaction.
6 . The method of claim 1 , wherein the user interface is configured to display, for each transaction in the set of transactions, an agent associated with the transaction.
7 . A method comprising:
generating tags having tag values for each transaction in a plurality of transactions by applying classifiers in a library of classifiers to the plurality of transactions, each transaction representing a conversation organized into scoring units;
determining a set of transactions from the plurality of transactions that are associated with an attribute value for a transaction attribute and that have a date that falls within a trend period;
calculating category summaries for the attribute value, each category summary of the category summaries being based on an aggregation of tag values of a tag of the tags for the transactions in the set of transactions; and
providing a user interface for the attribute value, the user interface configured to display the category summaries for the attribute value.
8 . The method of claim 7 , further comprising:
calculating a respective transaction score for each transaction in the set of transactions, the respective transaction score being based on the tag values and scoring criteria that apply to the transaction; and
determining aggregated transaction scores by aggregating respective transaction scores for transactions in the set of transactions that occur in a same aggregate period of the trend period,
wherein the user interface is further configured to display a trend line for the respective transaction scores that is based on the aggregated transaction scores.
9 . The method of claim 8 , wherein calculating the respective transaction score for each transaction in the set of transactions includes:
determining that a customized rubric applies to the transaction based on selection criteria for the customized rubric, the customized rubric including the scoring criteria; and
storing the respective transaction score and the tags for the transaction.
10 . The method of claim 9 , wherein, each tag is a tag generated by a classifier from the library of classifiers and, for at least some of the tags, the tag further identifies a weight associated with a tag value.
11 . The method of claim 8 , wherein the user interface is further configured to display a plurality of trend lines, the plurality of trend lines including the trend line, each trend line of the plurality of trend lines being based on aggregating respective transaction scores for a respective set of transactions that are associated with a respective attribute value for the transaction attribute.
12 . The method of claim 7 , wherein the user interface is further configured to provide a transaction attribute selection control configured to enable selection of the attribute value for the transaction attribute.
13 . The method of claim 12 , wherein the transaction attribute selection control is further configured to enable selection of the transaction attribute from a plurality of transaction attributes.
14 . The method of claim 8 , wherein the tags and tag values for the transactions are generated by applying classifiers associated with the tags to scoring units of the transactions, wherein applying the classifiers labels the scoring units with tag values.
15 . The method of claim 14 , wherein a value for at least one tag includes an indication of presence of the tag or an indication of absence of the tag.
16 . The method of claim 14 , wherein the classifiers include an emotional intensity classifier, wherein a tag generated by the emotional intensity classifier is based on a confidence in a prediction that a scoring unit includes an intense emotion.
17 . A system comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the system to perform operations including:
generating tags having tag values for each transaction in a plurality of transactions by applying classifiers in a library of classifiers to the plurality of transactions, each transaction representing a conversation organized into scoring units;
determining a set of transactions from the plurality of transactions that are associated with an attribute value for a transaction attribute and that have a date that falls within a trend period;
calculating category summaries for the attribute value, each category summary of the category summaries being based on an aggregation of tag values of a tag of the tags for the transactions in the set of transactions; and
providing a user interface for the attribute value, the user interface configured to display the category summaries for the attribute value.
18 . The system of claim 17 , the operations further comprising:
calculating a respective transaction score for each transaction in the set of transactions, the respective transaction score being based on the tag values and scoring criteria that apply to the transaction; and
determining aggregated transaction scores by aggregating respective transaction scores for transactions in the set of transactions that occur in a same aggregate period of the trend period,
wherein the user interface is further configured to display a trend line for the respective transaction scores that is based on the aggregated transaction scores.
19 . The system of claim 18 , wherein calculating the respective transaction score for each transaction in the set of transactions includes:
determining that a customized rubric applies to the transaction based on selection criteria for the customized rubric, the customized rubric including the scoring criteria; and
storing the respective transaction score and the tags for the transaction.
20 . The system of claim 18 , wherein the user interface is further configured to display a plurality of trend lines, the plurality of trend lines including the trend line, each trend line of the plurality of trend lines being based on aggregating respective transaction scores for a respective set of transactions that are associated with a respective attribute value for the transaction attribute.