About us

Bridging human and machine intelligence with eXplainable AI.

Our Mision

Our mission is to augment decision-making for financial institutions and beyond with proprietary eXplainable AI technology and remarkable human-computer interfaces.

Like a Mind, But a Machine

Senfino’s products are next-gen AI recommender and decision support systems with fully explainable and traceable decision reasoning that can be repositioned to any knowledge domain.

Management Team

Mark Zurada
CEO
Career Entrepreneur, Attorney, Engineer, Patent holder, and Congressional AI Policy Advisor
Tom Rutkowski
CTO
Career Entrepreneur, MSc in Comp Sci, MBA, PhD in AI, CFA Candidate
Michael Dobrovolsky
Chief Strategy
ex-Head of Machine Learning and Analytics and Morgan Stanley Global Wealth Management

R&D Advisors

Dr. Leszek RutkowskiProfessor
Dr. Jacek ZuradaProfessor
danuta
Dr. Danuta RutkowskaProfessor

And a team of 12 strategists, analysts, developers, designer,
architects and project managers

Our Peer-Reviewed Technical White Papers on the Global Conference Circuit

A Content-Based
Recommendation System Using
Neuro-Fuzzy Approach

Senfino Content Based Recommendation System Using Neuro-Fuzzy Approach provides human machine interpretable explanation in an AI assistant context. Our Neuro-Fuzzy architecture delivers substantial performance improvements returning acutely accurate personalized content and recommendations based on individual behavior without relying on collaborative filtering (crowd sampling).

Towards Interpretability of
the Movie Recommender Based
on Neuro-Fuzzy Approach

Senfino Fast Computing Framework for Convolutional Neural Networks (FCFCNN) embodies unique XAI architecture reducing processing overhead while accelerating forward signal flow. Neurons store reference pointers to corresponding regions of previous input propagating signal flow, eliminating the need to search for connections between layers. Additionally, reference points are batched along with feature maps in multi-feature input containers and treated as vectors, speeding calculations across CNN layers. In benchmark tests of image validation, FCFCNN performed twice as fast as the leading OverFeat CNN.

On Explainable Recommender Systems
Based on Fuzzy Rule Generation
Techniques

This paper presents an application of the Zero-Order Takagi-Sugeno-Kang method to explainable recommender systems. The method is based on the Wang-Mendel and the Nozaki-Ishibuchi-Tanaka techniques for the generation of fuzzy rules, and it is best suited to predict users’ ratings. The model can be optimized using the Grey Wolf Optimizer without affecting the interpretability. The performance of the methods has been shown using the MovieLens 10M dataset.

Get in touch

New York

The epicenter of Commercialization is where
Senfino honed its craft of driving new, value-
creating ideas through innovative deep tech.

Warsaw

Warsaw is home to the best artificial
intelligence and development talent –
recently ranked a Top 3 Market worldwide.