intesol.kr
Cases / Retail · E-commerce
Automation CASE 05

Inventory cost down 45%, revenue up 132%

Demand-forecast inventory management, support automation, and personalised marketing rolled into a fashion e-commerce platform in stages over 12 months. Monthly revenue went from ₩1.2B to ₩2.78B.

132%
Monthly revenue growth
45%
Inventory cost cut
68%
Faster response
Duration
12 months
Team
3 people
Started
2025 Q1
Market
Korea fashion commerce
SITUATION

What was blocking them

ISSUE 01
Season stock kept piling up
Forecasting relied on a buyer's instinct, and end-of-season sell-through sat at 62%. Whatever was left went to discount.
ISSUE 02
Inquiries outran capacity
Of 1,400 daily inquiries, 62% were repeats about delivery status or exchange rules — all answered by people.
ISSUE 03
Marketing was one broadcast
The same message went to everyone with no segmentation, and click-through had stalled at 1.1%.
APPROACH

The order we worked in

Each phase began from what the previous phase measured. We kept that order because without the earlier step there is no way to verify the next one's effect.

01
Demand forecasting
Three years of sales history combined with weather and search-volume data drives a weekly SKU-level forecast. It does not replace the buyer's decision; it gives them the reasoning.
4 months
02
Support automation
The 62% of repeat inquiries moved to automated answers, while anything needing judgment reached an agent with the context already summarised.
3 months
03
Personalised marketing
Segments split by purchase cycle and category preference, with messages branching per segment. Total send volume actually went down.
3 months
04
Operational handover
Operating metrics and tuning control for all three pipelines went to the client's team. Retraining happens in-house from here.
2 months
RESULTS

Baseline at kickoff, measured after delivery

Metric
Before
After
Monthly revenue
₩1.2B
→
₩2.78B
Inventory holding cost
baseline
→
-45%
Avg. response time
18 min
→
5.8 min
Marketing click-through
1.1%
→
4.3%

How each figure is measured is set out in the measurement notes on the cases page. Revenue and cost figures come from the client's own accounting and are published only within the scope they approved.

“They use it not because the forecast is always right, but because it shows why it forecast that.”
Retail · E-commerce · Director of e-commerce operations
Demand forecasting Support automation Personalised marketing Segment design Operational handover
Free · 1 business day
This one started with a diagnostic too
AI Workflow Automation starts by measuring your baseline. Find out where you stand first — the diagnostic is free.