Activity mining: separating system actions from human work in your order timeline.
Order timelines mix system actions with human work. Activity mining separates the two, and the human work is where the cost lives.
Why your timeline is two timelines.
An order event log looks like a single sequence: created, paid, fulfilled, shipped, delivered. But every event carries an actor, the entity that performed the action. Some actors are systems (Stripe captured payment, the cron job fulfilled the order, the carrier scanned the package). Others are humans (the warehouse picker pulled the SKU, the QA team flagged a defect, the support agent applied a manual override).
System actions are instant, deterministic, and free. Human actions take time, vary, and cost. When operators look at the timeline as a single stream, the two types blur. Activity mining pulls them apart.
What “activity mining” actually is.
Activity mining classifies every event in your order timeline by:
- Actor type, system, human, external party (carrier, supplier, customer)
- Temporal pattern, instant, scheduled, manual
- Batch detection, was this action part of a batch process (1000 orders fulfilled in 4 seconds) or genuinely one-at-a-time
Once classified, you can ask questions you couldn’t before: “what’s the total human time per order across our process?”, “which steps are still manual that should be automated?”, “where is exception handling concentrated?”
What it shows you that simple timing doesn’t.
Without activity mining, you see a 6-hour gap between “paid” and “fulfilled” and you might conclude your warehouse is slow. With activity mining, you can see that:
- 5 hours 53 minutes of the gap is a scheduled cron job that batch-fulfils every 6 hours
- 7 minutes is human pick-pack time
- The “slow warehouse” diagnosis was wrong, the warehouse is fast; the cron schedule is wrong
The fix is a 5-minute config change to a 1-hour cron schedule, not a $30K capacity increase at the warehouse. Activity mining lets you find this before you spend the $30K.
Common patterns activity mining surfaces.
| Pattern | What it looks like | Typical fix |
|---|---|---|
| Batch lag | 1000 orders fulfilled in 4 sec, hourly | Tighten cron schedule |
| Manual override hotspot | One agent handles 60% of manual fulfilments | Document the pattern they’re catching, automate it |
| Hidden exception flow | 15% of orders skip the standard path | Identify why, address root cause |
| Idle handoff | 30-min gap between human task and next system action | Trigger downstream automation on completion |
| Duplicate human review | Two agents touching same order in different tools | Consolidate tooling or hand-off |
Where the leverage is.
The largest financial wins from activity mining usually come from one of three places:
- Cron-scheduled batches with too-long intervals, fixing one scheduler can compress the median order-fulfilment cycle by 4-8 hours
- Manual review concentrated in specific edge cases, the team is doing pattern-matching that should be a 20-line rule
- Hand-offs without triggers, work-completed events that don’t kick the next stage into action
Halia’s activity mining module ingests order events from your connected platforms, classifies each by actor type using the metadata exposed by Shopify/WooCommerce/ShipStation, and surfaces findings ranked by total dollar impact across your order volume.
Activity mining questions, answered.
How is activity mining different from process mining?
Process mining maps the flow of events through your operation. Activity mining classifies each event by who or what performed it. The two are complementary, process mining tells you the sequence; activity mining tells you the work content of each step.
Can I do activity mining manually?
Yes, but it’s tedious. You’d export your order event log, tag each event row by actor type, then build pivots to summarise human time per order. A senior ops analyst can do this in 1-2 weeks for a sample of 1,000 orders. Automated tools do it continuously across all orders.
Do all e-commerce platforms expose actor metadata?
Most do partially. Shopify’s Order events include user_id when an action is human-triggered (vs. null for system actions). WooCommerce exposes similar metadata in its REST API. ShipStation tags shipment events with the user who created them. The metadata is rarely surfaced in standard dashboards but it’s in the event payload.
What's the biggest gain operators see from activity mining?
In our data, the largest single wins are typically scheduled batch jobs running too infrequently, fixing a cron schedule can shave 4-12 hours off median order fulfilment time at zero operational cost. The second-largest category is concentrated manual review that should be automated.
Does Halia's activity mining work without a 3PL?
Yes. The minimum viable input is order events from your storefront (Shopify, WooCommerce) and your payment processor (Stripe). 3PL integration improves the analysis for fulfilment-stage activities but isn’t required to get started.
See these patterns on your store.
Connect in 5 minutes. First findings the same day. Free under $50K MRR.
Start free →