Technology transparency

What powers Sympheny — and what doesn't.

A clear explanation of how Sympheny uses mathematics, data intelligence, and machine learning — and precisely what happens to your data.

Urban Sympheny AG
Sympheny Platform
Audience
Customers, partners & procurement
Version
2026
How Sympheny works

Three distinct layers — each transparent and purposeful.

Sympheny operates across three layers. Only the first is involved in the actual calculations. The other two support data preparation and, optionally, demand forecasting — never the optimisation itself.

Layer 1

MILP mathematical optimisation

Always active

The core of Sympheny is a Mixed-Integer Linear Programming (MILP) engine — a rigorous mathematical approach used in engineering and operations research. It finds the optimal energy system configuration given your technical, economic, and regulatory constraints.

Every result is fully deterministic and auditable: the same inputs always produce the same outputs, and every recommendation can be traced back to its underlying equations. There is no black box, and no AI in the calculations.

Deterministic Fully auditable Physics-based No AI in calculations
Layer 2

Data intelligence & clustering

Always active — data stays local

To handle real-world energy data efficiently, Sympheny applies established statistical clustering methods — including OPTICS, DBSCAN, k-medoids, and k-means — to identify typical demand patterns and load profiles from your input data.

These methods are developed and maintained entirely in-house by the Sympheny team. Your data is processed within the platform and is never transmitted to external models or used to train any system.

In-house algorithms Your data stays yours No third-party AI OPTICS · DBSCAN · k-medoids · k-means
Layer 3

ML demand forecasting

Opt-in only

When enabled by you, Sympheny can apply machine learning models to assist with demand forecasting. These models were trained exclusively on synthetic and research-generated data from controlled studies — never on data from any customer engagement.

This feature is inactive by default. You choose whether to enable it, and that choice does not affect the platform's core optimisation capabilities.

Opt-in — disabled by default Synthetic training data only Developed in-house Customer data never used for training
Our data commitments

Four promises we make to every customer.

Your data is never used for training

No customer operational data — energy profiles, building data, or project inputs — is ever used to train any model, ours or third-party.

Full result auditability

Every optimisation output can be traced to its mathematical inputs and constraints. We can explain every recommendation.

You control the intelligence level

ML features are opt-in. The platform's core capabilities are available in full without activating any machine learning component.

Built in-house, not outsourced

All algorithms and models are developed by the Sympheny team. We do not embed third-party LLMs or AI services into the computation pipeline.

"

Sympheny is built on a mathematically rigorous MILP core, enhanced with in-house data intelligence and optional ML-based demand forecasting — with full transparency and without ever using customer data for model training.

Customer FAQ

Questions about AI & data in Sympheny.

Straightforward answers to the questions we hear most often from customers, partners, and procurement teams.

Data & privacy

Is my operational data used to train Sympheny's models?

No. Customer data — energy profiles, load curves, building inputs, or any project-specific information — is never used to train any model. This applies to all features of Sympheny, including the optional machine learning layer.

Does Sympheny send my data to any external AI service or third-party model?

No. All computation, including the clustering and pattern recognition methods, runs within the Sympheny platform using our own algorithms. No customer data is transmitted to external AI providers, large language models, or cloud-based inference services.

What data was used to train the machine learning models?

The ML demand forecasting models were trained exclusively on synthetic datasets generated through research projects and controlled simulations. No real customer data was used at any stage of model development or validation.

Note: If you require a formal data processing addendum or documentation for procurement purposes, Sympheny can provide this upon request.

Where is my data stored and processed?

Project data is hosted on AWS in Stockholm by default, with Swiss and other regional deployment options available for enterprise customers. Storage and processing details are governed by your specific service agreement — contact your account representative for specifics.

About the technology

Is Sympheny an AI tool?

No — Sympheny is a mathematical optimisation platform. Its core is a Mixed-Integer Linear Programming (MILP) engine — a well-established, deterministic approach used in engineering and operations research worldwide. Some supplementary features use statistical clustering methods and, optionally, machine learning for demand forecasting. The calculations themselves are not AI.

What do you mean when you mention AI features?

The term refers narrowly to two things: the data intelligence layer (clustering algorithms such as OPTICS, DBSCAN, and k-means that structure your input data automatically) and the optional ML demand forecasting module. Neither replaces the mathematical optimisation — they support data preparation and demand estimation upstream of the MILP solver.

Can I explain the results to my client or regulator?

Yes. Because the core optimisation is MILP-based, every result is fully traceable: you can point to the specific constraints, cost parameters, and energy balances that led to a given recommendation. Sympheny does not produce outputs that cannot be explained from first principles.

Who built the algorithms — is this based on a third-party AI platform?

All algorithms and models are developed and maintained by Sympheny's engineering team. We do not use embedded third-party AI services (such as GPT, Gemini, or similar large language models) within the computation pipeline.

Opting in & out

What happens if I don't enable the ML features?

Nothing changes in terms of core functionality. Sympheny's MILP optimisation and clustering-based demand aggregation operate fully independently of the machine learning layer. The ML module is additive — its activation has no bearing on the platform's fundamental capabilities.

How do I enable or disable the ML demand forecasting feature?

ML features are disabled by default and can be enabled within the platform settings for a given project. Your Sympheny contact can walk you through the configuration options. Enabling the feature does not change how your data is handled — it remains within the platform and is not used for training.

If I enable ML features, does that mean my data contributes to future model improvements?

No. Enabling ML features activates inference only — the model makes predictions based on your data within your session. Your data does not flow back to retrain or update any model.

Note: In short: enabling ML means the model works for you — your data does not work for the model.

Procurement & compliance

Can Sympheny provide documentation for our AI governance or procurement process?

Yes. Sympheny can provide a technical description of the platform's AI components, a data processing summary, and — where required — a formal Data Processing Agreement (DPA). Please contact your account representative to initiate this.

Is Sympheny compliant with the EU AI Act?

Sympheny monitors regulatory developments including the EU AI Act and is committed to maintaining compliance as requirements come into force. Given that Sympheny's core is a deterministic mathematical model with limited and opt-in ML components, it is designed to align with transparency and auditability requirements. For formal compliance documentation, please contact us directly.

Who can I contact with further questions?

For technical, legal, or procurement questions about data handling and AI usage in Sympheny, please reach out to your Sympheny account representative or contact us at contact@sympheny.com.

Need procurement documentation?

We can provide a Data Processing Agreement, sub-processor list, and a technical description of the platform's AI components on request. Talk to us before procurement — we make the review easy.

Book a demo View sub-processors contact@sympheny.com