Logistics and supply chainBI, AI and ML for the business
Stock coverage and low-stock alarms
Sales and stock by item already live in the ERP and the warehouse system. Muvia works out every day how many days of cover each item has left, opens an alarm when it drops below the threshold and closes it by itself once goods arrive, with who handled it in the register.
Illustrative scenario: it describes a typical case, not a customer project.
You see the empty shelf when it is already empty.
Stock and sales are both there, but in two different systems. Whoever reorders looks at today's stock, not at how many days it will last at the current pace of sales, and the shortage shows up when a customer asks for an item that is not there.
A fixed threshold on quantity does not help: for a fast seller a hundred units are one day, for another they are three months. You need cover in days, item by item, and an alarm that does not keep ringing while the goods are already on their way.
- Who it's for
- Warehouse managers, purchasing and supply chain planning.
In Muvia, step by step
Real product screens, recorded on a project with sample data.
The video · Sales and stock by item already live in the ERP and the warehouse system. Muvia works out every day how many days of cover each item has left, opens an alarm when it drops below the threshold and closes it by itself once goods arrive, with who handled it in the register.
What you get
- Cover in days, not units
- Every item is read at its own pace of sales: a hundred units can be one day or three months, and the dashboard says which.
- Alarms without the noise
- The episode opens below the threshold and closes by itself once goods arrive: no alarms that flare up at every swing.
- The problem has a name
- When episodes cluster on one family, the dashboard leads to the supplier delivering late or short.
- Everything stays on record
- Every episode stays in the register with who took it, how they classified it and what they noted.
For the technical team
How it is built in Muvia
- 1
Connect sales and stock
The ERP and the warehouse database become sources copied every night, incrementally and over an encrypted connection. Thresholds by family arrive as an Excel file; every source becomes a table.
- 2
Work out cover in steps
In a step-built query, line up the 28-day moving average of sales and the ratio of stock to average sales: the days left, item by item. Every step shows its own result.
- 3
Set an alarm that closes by itself
A flow checks cover after every refresh: the episode opens below 7 days and closes only above 10, so it does not reopen at every small swing.
- 4
See where it piles up
A dashboard shows how many alarms are open day by day, the most exposed items and a heatmap by family and week: a supplier's problem is easy to spot.
- 5
Handle episodes in the register
In the alarm register, whoever takes an episode classifies it and notes the cause, such as a supplier delivering late. The Monday report sums up cover by family.
- The data it needs
- Daily sales by item and warehouse, from the ERP on SQL Server
- Stock by item and warehouse, from the warehouse database on PostgreSQL
- Item master with family and supplier, from the ERP
- Cover thresholds by product family, from an Excel file
More cases in this line
All use cases- Demand and stock forecastingSales history and stock levels are already in the ERP. Your data scientist builds a forecasting model with scikit-learn; Muvia runs it every night next to the data and puts forecast, actual sales and understock in front of the people who reorder.
- Supplier punctuality and OTIFReceipt lines already tell you who delivers on time and in full, provided the data is clean. In Muvia, rules on the data set aside the impossible rows, OTIF is worked out delivery by delivery, and the supplier ranking shows who is slipping and since when.
- Delivery times and carrier punctualityEvery shipment leaves a dispatch time and a delivery time, scattered between the warehouse and the carriers' files. Muvia brings them together: where time is lost between warehouse and customer, which carrier slows down in which area and from which week, and the carrier review already written.
Bring us a question you can't answer today.
We start from a real question your business has and walk the path from source to dashboard with your systems, not a demo dataset.