Our team developed a new part for an existing ERP platform from scratch, which covers the production structure, interrelationships between its components, cost calculation, and simulation.

Solution

Users can build a custom model of their factory, adding level by level – workshops, equipment, and modules. The scheme helps analysts understand the model of a factory better and allows references to be made at a glance.

PLANT STRUCTURE SCHEME

Clicking the items at the lowest level of the scheme, users open a section with accumulated information about each manufacturing unit: pages with a general overview of work and output, manufactured and defective products, materials used, losses, and labor. It is possible to set KPIs with different parameters (output, scrap, etc.) for each machine and use charts to track changes in absolute and relative terms. Analysts can check the efficiency of each machine: how many product

Details

The solution offers a dashboard summarizing production costs by period, including output, total costs, and costs per unit. Users can compare periods to track changes. A P&L table breaks down costs by labor, materials, and more versus budget and losses, with graphs for easy analysis.

Detailed P&L spreadsheets provide deeper insights, enabling cost calculations based on output, price changes, and losses.

COST MODULE

The spreadsheet interface is user-friendly, with buttons for editing, adding, repeating, and deleting rows. Complex formulas run in the backend, preventing accidental changes by regular users. Data import from CSV or XML reduces manual work.

The configuration includes common elements like labor, materials, energy, and expenses. Users can customize these by renaming, adding lines, and updating costs and prices to fit their needs.

INTUITIVE USER INTERFACE

The cost module enables simulation of top-down and bottom-up scenarios. Analysts set reduction targets (e.g., costs, losses) and estimate yearly cost optimization, helping production companies minimize expenses while maintaining quality and boosting EBITDA.

Approved scenarios serve as benchmarks to monitor current production efficiency, allowing analysts to identify major errors in effectiveness and timing.

SIMULATION MODULE

The client had a clear vision with mock-ups and formulas for the analytical module. We handled software architecture, technology selection, and full-stack development. Close collaboration between our Business Analyst with financial expertise and the client’s analysts transformed complex parameter relationships into an efficient backend calculation system with clear charts and tables on the interface.

PROCESS

In the discovery phase, we analyzed the client’s ERP and business processes, modeled entities, planned modules, and aligned workflows.

We selected ngx-datatable for flexible spreadsheet handling, D3.js for dynamic data visualizations, and TensorFlow.js for scalable machine learning. This ensured clear data presentation and faster decision-making

DISCOVERY PHASE AND TECHNOLOGY CHOICE

Our team implemented a Machine Learning module to speed up and improve data analysis by detecting patterns in plant operations and effectiveness. It learns from ERP data to identify trends that aid manufacturing cost optimization.

Operating within the manufacturer’s perimeter, the module analyzes only statistical data without storing or labeling specific branch or machine info, ensuring security and protecting sensitive client information

MACHINE LEARNING AND SECURITY

After agreement of the work breakdown structure with the client, we got down to developing the MVP. 
We delivered module by module every two weeks, discussed tasks in Slack and had weekly videoconferences in Google Meets. 
Each development phase concluded with the unit and manual testing, so we could detect and fix even the smallest bugs at the earliest possible stage, preventing them from turning into issues. 


TECHNOLOGY CHOICE

Designed for user-friendliness, the new module required just an hour of employee training. Within a week, report preparation became three times faster, giving analysts more time for data review and scenario simulation. This led to more precise findings and faster recommendations, boosting business value and customer loyalty.

The ERP system remained secure, as the machine learning algorithms only analyze patterns without accessing vital data.

Results

4 months from idea to a functional MVP development and launch
3 times faster preparation of reports, a more calibrated set of findings and recommendations within a shorter period of time



Figures

The client’s analysts struggled with slow, cumbersome Excel sheets for factory cost calculations, which required manual formula changes when adding new data, causing delays and errors.

To improve efficiency, the client proposed adding a customizable analytics module to their ERP system. This module handles detailed production analytics and forecasts, letting users input data while calculations run automatically in the backend, adaptable to any factory or process.

Challenge

Business Intelligence System for Plants

Innowise Sp. z o.o

As the lead developer on this project, I am proud to have delivered a user-friendly system that required just an hour of training for employees. Within a week of implementation, report preparation became three times faster, allowing users to focus on deeper data analysis and scenario simulations. This improvement empowered analysts to provide more precise recommendations quickly, significantly enhancing business value and customer satisfaction.

Anonymous

At Innowise we believe in the primacy and supremacy of human rights, ethics, and international norms. Thus, our software development company rejects and condemns any form of discrimination, be it racial, gender, religion, or any other oppression. We support diversity, freedom of expression, privacy, welfare, and human rights of all employees. 


Innowise Sp. z o.o

About

Challenge, approach, and impact

Challenge

How we built

Testimonials

Team structure

Client team

Tom

Agency team

4 x Backend Engineers

2 x Frontend Developer

2 x Business Analyst

1 x QA Engineer

Similar Case Studies

Chat with agency

Let's turn your ideas into reality—connect with our team.