Set up Escalation Predictor to Preempt Tickets
Any support agent who has worked in the field for a long time develops a gut feeling for cases that are quick to solve and cases that carry with them a risk of escalation. Such agents are worth their weight in gold. If you are a support manager and find such an agent, hire them right away. And if you cannot find such an agent, try Escalation Predictor.
Like an old hand, Escalation Predictor forewarns when a case is about to go south so you can take appropriate action to thwart an escalation.
Escalation Prediction needs to access cases before it can start analyzing them. In this section, you will connect the app with a case management system.
- Expand Apps, click Escalation Predictor, and then click Connect with a Content Source.
- Escalation Predictor works by an analysis of the historical cases in your system. Select a content source. NOTE. As of November, 2020, only Salesforce supported.
- To establish a correlation between cases and escalation, SearchUnify uses the
IsEscalatedcase field or a custom field created by Salesforce admins. Select that field and set its value to
IsEscalatedor a value that represents an escalation in your custom field.
- Escalation Prediction uses an advanced model which trains on cases' data. The more data there is, the more accurate the model will be. Start Date allows you to refine how much data to keep. Pick a date and click Next. Only tickets logged after Start Date will be analyzed.
Escalation Prediction trains on cases to find factors which led to escalations in the past. Depending on the case management system, the factors can easily run into the dozen. They frequently include a case's title, a product's category, and the purchase amount. All of these factors (or case fields) are put into one of the three available categories in the app: Textual (used for sentimental analysis), Categorical, and Numerical.
- Drag all the text fields, such as case titles, case description, and comments into Textual. The Categorical field is for fields like priority, product group, and category. Use the Numerical field for storing number of comments exchanged, purchase amount, and other fields with numbers.
The data after connecting Salesforce with Escalation Predictor.
Based on the cases data in Textual, Categorical and Numerical, Feature Classification generates visual reports. Review them to spot patterns. For instance, for an organization which prioritizes A, B, C, D and E; if D is the largest then the cases with priority D are more likely to escalate. Also, the keyword cloud based on an analysis of case messages help you identify the triggers which suggest an imminent escalation.
Scroll down to view them all.
In Scoring Data, the metrics to be used in forecasting are picked. A rule of the thumb is to check the metrics with high correlation and uncheck the ones with low correlation and then click Retrain Model.
Example: In the next image the most accurate predictor of escalation is Days to Respond, which stands at 21%. As the Days to Respond number goes up, so does the probability of an escalation. It's better to keep it checked. However, case fields that have little correlation with escalations can be removed. In the next image, Solutions Area can be unchecked.
Escalations Dashboard predicts the likelihood of escalations on incoming cases. The probability is encapsulated in a number in the last column. Hovering over the probability number shows how factor selected in Scoring Data has contributed to the final calculation.
The list on Escalation Dashboard presents high-priority cases. A way to improve CSAT number a great deal is to handle them first. You don't really have to log in find the cases because it's also possible to set email alerts and download the cases' list.
The only critical setting on this screen is the Minimum Threshold box. Too low a number will flood the screen with cases and by placing too high a number, you miss letting imminent escalations slip under the radar.
Last updated: Friday, November 27, 2020