Overview
The Active Case Count By Day calculator measures how many cases were actively in progress on each calendar day. A case is considered "active" on a given day if it has started but not yet completed - meaning the case has at least one event on or before that day and at least one event on or after that day.
This calculator is particularly valuable for understanding workload, identifying capacity constraints, and detecting bottlenecks. Unlike event-based calculators that count activities, this calculator counts unique cases that were in an ongoing state, providing insight into work-in-progress (WIP) levels over time.
Note: This is a hidden calculator in mindzie Studio, meaning it is not directly visible in the standard calculator menu but can be accessed programmatically or through advanced configurations.
Common Uses
- Monitor work-in-progress (WIP) levels to identify capacity bottlenecks and resource constraints
- Detect periods of excessive case backlog that may indicate systemic issues
- Analyze seasonal workload patterns to optimize staffing and resource allocation
- Identify the impact of process changes on case throughput and cycle times
- Validate that case completion rates keep pace with case creation rates
- Support capacity planning by understanding historical active case volumes
- Detect anomalies such as sudden WIP spikes that may indicate process breakdowns
Settings
This calculator has no configurable settings beyond the standard filter context. It automatically analyzes all cases in your filtered dataset by determining which cases were active (in progress) on each calendar day.
How Active Cases Are Calculated:
A case is counted as active on a specific date if:
- The case's first event occurred on or before that date (the case had started)
- The case's last event occurred on or after that date (the case had not yet completed)
- This means a case is active from its start date through its completion date (inclusive)
Standard Fields:
- Title: Optional custom title for the calculator output
- Description: Optional description for documentation purposes
Examples
Example 1: Identifying Capacity Bottlenecks
Scenario: Your order fulfillment process has been experiencing delays, and management wants to understand whether increasing case volumes are exceeding your team's processing capacity. You need to identify periods where active cases accumulate faster than they are being completed.
Settings:
- Title: "Order Fulfillment Work-in-Progress Analysis"
- Description: "Track active case levels to identify capacity constraints"
Output:
The calculator displays a table with two columns:
- Date: Each calendar day in your event log's time range
- Active Case Count: The number of cases that were in progress on that date
Example output:
Date Active Case Count
2024-01-15 487
2024-01-16 492
2024-01-17 501
2024-01-18 523
2024-01-19 558
2024-01-20 562
2024-01-21 559
2024-01-22 612
2024-01-23 648
2024-01-24 687
2024-01-25 724
Insights: The steadily increasing active case count from 487 to 724 over 10 days indicates that new cases are arriving faster than existing cases are being completed. This 49% increase in WIP suggests a capacity bottleneck. The acceleration in the rate of increase (from +5 cases/day early in the period to +37 cases/day later) shows the bottleneck is worsening. Management should investigate whether staffing levels are adequate or if a process issue is slowing case completion.
Example 2: Evaluating Process Improvement Impact
Scenario: Your team implemented a process automation on March 15th designed to reduce manual approval steps and accelerate case throughput. You want to measure whether the automation successfully reduced work-in-progress levels.
Settings:
- Title: "Process Automation Impact Assessment"
- Description: "Compare WIP levels before and after automation deployment"
Output:
The output shows active case counts for two weeks before and after the automation deployment:
Before automation (March 1-14):
Date Active Case Count
2024-03-01 856
2024-03-05 871
2024-03-10 883
2024-03-14 892
After automation (March 16-30):
Date Active Case Count
2024-03-16 879
2024-03-20 823
2024-03-25 761
2024-03-30 698
Insights: The automation had a significant positive impact. Before deployment, active cases were trending upward from 856 to 892 (4% increase). After deployment, active cases declined from 879 to 698 (21% decrease). The reduction in WIP indicates that cases are now completing faster than they arrive, suggesting the automation successfully improved throughput. The steady decline over two weeks shows sustained improvement rather than a temporary effect.
Example 3: Detecting Weekend and Holiday Patterns
Scenario: You're analyzing a customer service ticketing process and want to understand how weekends and holidays affect work-in-progress levels. This will help you determine whether to implement weekend coverage or allow natural fluctuations.
Settings:
- Title: "Customer Service WIP Weekly Pattern Analysis"
- Description: "Identify weekend accumulation patterns"
Output:
The calculator shows active case counts across a typical month. When visualized as a line chart, you observe:
- Active cases gradually increase Monday through Friday (from ~450 to ~520)
- Cases remain flat or slightly increase Saturday and Sunday (no work completed, but new cases may arrive)
- Monday shows a sharp spike (up to ~580) due to weekend accumulation
- The pattern repeats weekly
Sample data showing one week:
Date Active Case Count Day of Week
2024-02-12 452 Monday
2024-02-13 463 Tuesday
2024-02-14 478 Wednesday
2024-02-15 495 Thursday
2024-02-16 518 Friday
2024-02-17 527 Saturday
2024-02-18 531 Sunday
2024-02-19 587 Monday
Insights: The consistent weekly pattern shows that cases accumulate over the weekend (from 518 Friday to 531 Sunday, then spike to 587 Monday) because no cases complete but new tickets continue arriving. The Monday spike of 56 additional active cases (10% increase) creates a recurring capacity challenge. This pattern suggests either implementing limited weekend support to prevent accumulation, or ensuring adequate Monday staffing to handle the predictable spike. The consistent pattern across multiple weeks indicates this is a structural issue rather than a random variation.
Example 4: Analyzing Seasonal Capacity Requirements
Scenario: Your accounts payable process handles significantly higher invoice volumes during quarter-end periods. You need to quantify the seasonal WIP variations to justify temporary staffing increases during peak periods.
Settings:
- Title: "Quarterly Accounts Payable Capacity Analysis"
- Description: "Compare WIP levels during normal and quarter-end periods"
Output:
The output shows active case counts across a full quarter, revealing distinct patterns:
Normal period (mid-quarter):
Date Active Case Count
2024-02-15 245
2024-02-20 238
2024-02-25 251
Quarter-end period (last week of quarter):
Date Active Case Count
2024-03-25 312
2024-03-26 367
2024-03-27 423
2024-03-28 489
2024-03-29 537
2024-03-30 582
2024-03-31 641
Insights: Normal mid-quarter WIP averages around 245 active cases. During the final week of the quarter, WIP more than doubles, peaking at 641 cases on the quarter's last day (162% increase). The dramatic acceleration in the final week (from 312 to 641 cases, adding 329 cases in 6 days) shows that quarter-end creates extreme capacity pressure. This data justifies requesting temporary staff during the last week of each quarter, or implementing a "soft close" policy to spread invoice processing more evenly throughout the month.
Example 5: Identifying Data Quality Issues
Scenario: Your data engineering team recently migrated event log data from a legacy system. You want to verify that the migration correctly preserved case lifecycle information and didn't create artificial gaps in case continuity.
Settings:
- Title: "Data Migration Validation - Case Continuity Check"
- Description: "Verify active case counts are logical and continuous"
Output:
The calculator reveals an anomaly in the data:
Date Active Case Count
2024-01-10 1,247
2024-01-11 1,289
2024-01-12 1,312
2024-01-13 47
2024-01-14 52
2024-01-15 1,278
2024-01-16 1,301
Insights: The sudden drop from 1,312 active cases to 47 on January 13th, followed by an immediate recovery to 1,278 on January 15th, is impossible in real business operations. A 96% overnight decrease in WIP followed by a 2,359% increase the next day indicates a data migration issue. Most likely, events for January 13-14 were not properly migrated, causing cases to appear artificially completed on January 12th. The data engineering team should investigate the migration scripts for those specific dates and re-import the missing events.
Output
The calculator produces a data table with the following columns:
Date (DateTime): The calendar date for each day in the event log's time range. The time component is always set to 00:00:00 (midnight) as the calculator groups by date only. Dates span from the earliest event timestamp to the latest event timestamp in your filtered dataset.
Active Case Count (Number): The count of unique cases that were in progress on that date. This includes all cases where the case start date is on or before the date, and the case end date is on or after the date. Cases are counted once per day regardless of how many events they had on that day.
The output can be visualized as:
- Line charts: Ideal for identifying trends, patterns, and anomalies in WIP levels over time
- Area charts: Effective for showing the volume of work-in-progress as a filled region
- Bar charts: Useful for comparing WIP levels across specific date ranges or time periods
- Trend analysis: Apply moving averages to smooth daily variations and identify underlying patterns
- Statistical summaries: Calculate mean, median, and standard deviation to understand typical WIP levels and variability
Interpretation Tips:
- Increasing trend: Cases are arriving faster than they complete (capacity issue or bottleneck)
- Decreasing trend: Cases are completing faster than they arrive (excess capacity or reduced demand)
- Stable pattern: Process is in equilibrium with balanced arrival and completion rates
- Sudden spikes: May indicate data quality issues, process breakdowns, or unusual events
- Weekly patterns: Often reveal weekend effects or staffing variations
- Seasonal patterns: Show cyclical business demands that require capacity planning
Note: Cases with missing start or end timestamps may be excluded from the analysis or counted incorrectly. Ensure your event log has valid timestamps for all events to get accurate active case counts.
This documentation is part of the mindzie Studio process mining platform.