When Dayforce is configured to generate service patterns from historical data, you don’t need to define service patterns. Instead, Dayforce uses one of your organization’s key performance indicators (KPIs), such as number of transactions, to determine appropriate staffing levels.
Dayforce tracks the KPI data and aggregates it into quarter-hour segments. For example, if the number of transactions is the KPI used for service patterns, Dayforce aggregates a location’s historical point-of-sale data for each quarter hour. With this data, we can start to see what the service pattern looks like: if 50 transactions were recorded between 6:00 PM and 6:15 PM, but only 10 between 9:00 AM and 9:15 AM, the location’s staffing requirements for 6:00 PM are higher than for 9:00 AM.
Dayforce takes several weeks of historical data for the relevant KPI, and looks at the data for each time segment at a time. So, if last week’s Monday 9:00 AM to 9:15 AM had 25 transactions, 32 transactions two weeks ago at the same time, and 35 the week before that, it can use this trend to predict the number of transactions for this week’s Monday.
Finally, it takes the predicted values for the quarter-hours, determines the relative difference between them, and generates a service pattern. So, a time segment with 50 predicted transactions has double the staffing requirements compared to a segment with 25 predicted transactions.