Proof & Research

Built on Evidence, Not Assumptions

INSYTES is founded on the belief that industrial AI must be provable, explainable, and trustworthy. Our technology is grounded in peer-reviewed research, validated through real-world data.

Scientific Origins

The core technology behind INSYTES and its product, Cauza, originates from doctoral research in causal discovery and decision intelligence.

This research focused on:

Identifying true cause-and-effect relationships in complex systems
Moving beyond correlation-based analytics
Enabling transparent and auditable decision support

Research Impact in Practice

Our research is not theoretical. The same causal frameworks documented in publications have been applied to:

Manufacturing energy optimization
Fleet emissions reduction
Root-cause discovery in production systems
Decision support under uncertainty

This ensures a direct link between academic rigor and industrial value.

Peer-Reviewed Publications

Our methods and results have been published in recognized scientific journals.

A comprehensive causal AI framework for analysing factors affecting energy consumption and costs in customised manufacturing

International Journal of Production Research (2025)

Read Paper

From Theory to Practice: Implementing Causal AI in Manufacturing for Sustainability

Procedia Computer Science (ACM) (2025)

Read Paper

These publications demonstrate the application of causal AI in real industrial and societal systems, not synthetic benchmarks.

Theses & Dissertations

Academic research that forms the foundation of INSYTES technology.

Causal AI for Smart Decision-Making: Driving Sustainability in Urban Mobility and Industry

Tamas Fekete • PhD Dissertation

Constructor University Bremen

View Thesis

Causal Artificial Intelligence for Industrial Decision-Making: A Comparative Study of Predictive, Causal, and LLM-Guided Approaches

Mohamed Goda Ebrahim • Bachelor Thesis

Constructor University Bremen

Methodology Overview

INSYTES combines multiple layers of intelligence

Causal Discovery

Identification of structural cause-and-effect relationships from observational data

Causal Inference

Quantification of the effect of interventions and changes

Counterfactual Reasoning

Evaluation of "what-if" scenarios before action is taken

Explainability

Human-readable explanations aligned with domain understanding

Each layer is designed to be transparent, inspectable, and defensible.

Validation Beyond Publications

INSYTES' work has been reviewed and validated through multiple channels:

Peer review by independent academic experts
Evaluation by public innovation programs
Pilot projects with industrial partners
Acceptance into research-driven startup accelerators

This multi-layer validation ensures robustness beyond a single benchmark or study.

Alignment with Responsible AI

INSYTES' research and product design align with emerging EU AI governance principles.

Explainability by design
Traceability of decisions
Human-in-the-loop understanding
Avoidance of black-box recommendations

Causal reasoning is a cornerstone of responsible, trustworthy AI.

Why This Matters

Safety
Cost
Sustainability
Reliability

Industrial decisions affect all of these. INSYTES ensures those decisions are supported by:

Scientifically validated methods
Transparent reasoning
Evidence that can be questioned and verified

This is the difference between analytics and decision intelligence.

Learn More

Interested in the science behind Cauza or exploring collaboration opportunities?