There are two methods to get burnout metrics of groups in Yva.ai API:
To use these methods you will need to specify the start date (sould be Sunday) and the end date (should be Saturday).
Both methods allow to get metrics for each week of the period such as:
- Burnout stage,
- Number of weeks in current burnout stage,
- Data sufficiency indicator,
- Yva burnout index,
- Yva activity index.
Burnout stage - this metric is a result of Yva burnout index (YBI) and Yva activity index (YAI) periodic values
Burnout stage duration - is calculated as the number of the last finished week minus the number the week with the last change of Burnout stage
Data sufficiency - calculation is based on the median weekly value of sent emails for the observed period and the length of the period
Yva burnout index - is the result of operation of convolutional neural network built on the 40*N parameters, or rather, on their 40N-dimensional time vectors. Convolution is done so as to maximize the F-measure of resignation prediction.
Yva activity index - is formed on the basis of "physical" changes in the digital footprint. Scalar model for calculation of this index is based on 40*N parameters, where N is the number of sources. Linear regression examines five periods using 8 independent variables: workday commencement time, workday length, work visibility, response time, etc.
Case 1 - an example of no burnout
The Burnout Index of the employee has always been positive, while the Activity Index is usually positive and even has been growing over the past few weeks. There are no signs of burnout or frustration. The employee is apparently not a candidate for the job market. He can leave the company only if actively lured away or unexpectedly given a unique and exciting job offer.
Case 2 - an example of decreased activity
The employee's Burnout Index is positive, but it is falling over the past three months. The Activity Index is positive during the first half-year observation period, but then decreases and even becomes negative. There are no signs of burnout or frustration yet. However, it is important to keep an eye on current decline in the indices, and monitor behavior of the indices in subsequent periods in order to react on time in case of their further fall.
Case 3 - an example of significantly decreased activity and early burnout
The Activity Index denotes signs of the employee's frustration since the summer 2020 onwards. The system detects signs of early burnout since mid-October. An employee with such a diagram may be a passive candidate for the job market, so likelihood of his voluntary resignation will depend on the labor market context and his particular situation (for example, family or financial responsibilities).
Case 4 - an example of late burnout
The Activity Index denotes signs of the employee's frustration since the mid-spring 2020 onwards. The system detects signs of early burnout since the beginning of June, and signs of late burnout since August 2020. During the last few weeks there has been an upward trend in the Activity Index (i.e., decrease of “pessimism” rate). Such a diagram can mean either beginning of changes for the better at the current place or “handing over the duties” before leaving. For an adequate assessment of the real situation, you should have more information about the employee's track in the company and about current developments.