Data & Model

How the estimate is produced

Model v0.1 is illustrative. Cost logic derived from standard cost-engineering formulas. Connect your historical catalogue to train a data-driven model.

Current model

Illustrative
Version
v0.1
Type
Rules-based
Basis
Cost-engineering formulas
Processes
3
Materials
13
Updated
14 Jul 2026

What drives the estimate

  1. 1Net / pour weight27%
  2. 2Manufacturing process21%
  3. 3Material grade15%
  4. 4Annual volume11%
  5. 5Cut length / perimeter9%
  6. 6Feature count · holes, bends, darts8%
  7. 7Wall / sheet thickness5%
  8. 8Tolerance class3%
  9. 9Coating / surface treatment1%

Connect your cost catalogue

Drop a catalogue file here: .csv, .xlsx, or connect a database

One row per historical part, with the columns below.

Expected columns
13
part numberprocessmaterial gradethicknesscoatingweightsurface areacut lengthfeature countannual volumeregionactual costdate

With ~2,000 historical parts a trained model typically reaches ±8 to 12% mean absolute error against quoted price.

Connect a system of record

1 of 8 connected

Cost data is never in one place. Geometry and revisions live in PLM, rates and paid prices in ERP, quotes in sourcing. Mūlya reads from each rather than asking you to assemble a spreadsheet.

Teamcenter

Siemens · PLM

Connected

Part master, revisions, CAD documents, BOM structure, change records

Feeds Part Library · Estimate History · Compare Revisions

SOA / Active Workspace REST50 parts · 63 revisions
Windchill

PTC · PLM

Available

Part master, revisions, CAD documents

Feeds Part Library · Estimate History

Info*Engine REST
SAP S/4HANA

SAP · ERP

Available

Purchase order history, actual paid prices, material master, vendor master

Feeds Rate Master · estimate-vs-actual · Data & Model training set

OData / CDS views
SAP Ariba

SAP · ERP

Available

RFQ responses, awarded prices, supplier capability

Feeds Supplier pack responses · quoted price benchmark

Ariba Network API
Snowflake

Snowflake · Warehouse

Available

Curated historical cost catalogue, cleaned and joined

Feeds Data & Model · the trained model's training set

JDBC · key-pair auth
PostgreSQL

Self-hosted · Warehouse

Available

Any tabular cost history you already maintain

Feeds Data & Model

Direct connection · read-only role
CSV / Excel

File upload · File

Available

One-off catalogue extract, no integration work

Feeds Data & Model

Browser upload · column mapping on import
Mūlya REST API

Mūlya · API

Roadmap

Estimates out: into your own dashboards or a PLM property

Feeds Outbound: writes the estimate back onto the part in PLM

REST · OAuth 2.0 client credentials

Connections are read-only by design. Mūlya never writes to your systems of record, except the roadmap REST API, which writes the estimate back onto the part in PLM once you ask it to.

Roadmap to a trained model

Step 1 of 4
  1. 1
    Catalogue ingestion & cleaningawaiting data
  2. 2
    Feature engineeringawaiting data
  3. 3
    Model training & validationawaiting data
  4. 4
    Accuracy reporting vs. actual quotesawaiting data