Agent Skill Enhancement Model [arn-post-tag id=12]
So far, your Service Insights dashboard provided you with a comprehensive picture of your workforce performance, including:
- Who overperforms while others struggle?
- How does your team’s performance compare to other teams?
But now what?
Assigning objectives to your agents definitely helps them keep track of their performance. Still, you’re missing out on actionable insights, and ultimately your main goal:
- How to best improve your team’s performance?
- What specific skills should they work on improving?
This is what we have coming up in this new release: upskill your workforce with minimal resource expenditure.
With this tailored training plan per agent, you’ll be able to identify how to most effectively level up your workforce’s KPIs.
Tailored Training Plan
Our innovative model defines the perfect training plan for your workforce (Field Service only) by identifying the best effort/impact equation, based on Aquant’s Workforce Performance Index (WPI) score. Basically, we’re providing you with measurable and actionable goals for each agent to level-up their KPIs, for each product.
The model will raise observations whose improvement can best boost performance in one of the following KPIs:
- First Time Fix Rate (FTF)
- Part Cost
- Labor Cost
Let’s have a look at Blake Munoz, specialized in the NextGen 1kW Turbine product.
Over the next 3 months, the model identified he can boost his overall FTF by almost 20%. How? The table below retrieves the observations he should focus on.
As a manager, you are also able to check out how far Blake Munoz is from the average performance of his colleagues, along with the best performance, for each recommended observation.
Repair Outcome Prediction Model [arn-post-tag id=12]
All our KPIs are impacted by one crucial piece of information: should the service visit mentioned in your dataset be considered a success or a failure? Specifically, will the customer call again within the next 30 days (or any custom success metric) following this last visit?
Using this criterion, it was not possible to determine the success or failure of an event that occurred less than 30 days ago. So far, two options were considered in this case:
- Exclude these events, leading to an incomplete dataset
- Consider them as success, implying quite an optimistic last month
Level-Up Data Precision
We’re proud to introduce our much anticipated Repair Outcome Prediction model that predicts whether these last events are more likely to be successful or not.
Based on historical data for observations, product type, and asset history, this new model increases our accuracy in many areas around Service Insights and provides better understanding of performance throughout the entire dataset timespan.
Planning for the following months will become an easy game!
Improving Data Veracity and Accuracy [arn-post-tag id=11]
Data is tough, and raw data is even tougher since it often misses some information or shows inconsistencies.
As part of our ongoing journey to enhance data trust and precision, we’ve upgraded our system to automatically fill and predict missing values, this time around parts consumption. Fewer gaps lead to more data points and more accuracy in your dashboard analysis.
Any feedback on our new releases?
Please feel free to reach out to us and we’ll set up a Q&A session along with your Customer Success Manager.