---
title: "It From Bit, Research & Publications"
publisher: "It From Bit d.o.o."
publisher_url: "https://itfrombit.biz/about/"
canonical_url: "https://itfrombit.biz/research/"
summary: "Peer-reviewed work in operations research, AI, and decision intelligence."
license: "all-rights-reserved"
---
> *Canonical HTML version: [https://itfrombit.biz/research/](https://itfrombit.biz/research/). © It From Bit d.o.o.. All rights reserved.*

# It From Bit, Research & Publications

The work is grounded in published research. Selected peer-reviewed contributions from each practice area are listed below; consult Google Scholar for the founder's full record.

## Selected publications

### Comparative Analysis of Modern Machine Learning Models for Retail Sales Forecasting (2026)

Mario Brcic, Luka Hobor, Lidija Polutnik, Ante Kapetanovic. *Croatian Operational Research Review*, 2026.

A triage framework for model selection in retail demand forecasting under real-world conditions: intermittent demand, missing data, and production constraints. Across major retail datasets, tree-based ensemble methods (XGBoost) consistently outperform deep learning architectures, a finding with direct implications for how organizations choose forecasting infrastructure. Co-authored with Babson College and mStart (Fortenova Group).

- arXiv: https://arxiv.org/abs/2506.05941

### AI-Assisted Unit Test Writing and Test-Driven Code Refactoring: A Case Study (2026)

Ema Smolic, Mario Brcic, Luka Hobor, Mihael Kovac. *MIPRO 2026*.

Documents a client engagement in which AI coding models generated approximately 16,000 lines of unit tests in hours rather than weeks, enabling safe large-scale refactoring with up to 78% branch coverage. A practical template for organizations managing legacy codebase risk with AI tooling.

- arXiv: https://arxiv.org/abs/2604.03135

### Policy-Bound Triple-Entry Receipts for Autonomous Commerce (2026)

D. Kapusta, Mario Brcic. Working paper. With COTRUGLI Business School and HashNet.

Proposes an accounting control architecture for AI-mediated transactions where execution speed outpaces human governance. The Policy-Bound Triple-Entry (PBTE) method uses an Accounting State Machine to gate transaction recognition against pinned policies, enabling event-time governance across ERP systems. Foundational work for agentic commerce infrastructure.

- ResearchGate: https://www.researchgate.net/publication/400806541_Policy-Bound_Triple-Entry_Receipts_for_Autonomous_Commerce

### Responsible and Ethical AI: The Strategic Differentiator for Premium Brands (2023)

It From Bit white paper.

How premium brands can implement responsible AI governance to foster authenticity, align AI systems with core values, and gain measurable competitive advantage. Covers regulatory compliance, stakeholder trust, human-centric AI design, and practical implementation strategies.

- HTML: https://itfrombit.biz/research/responsible-ai-whitepaper/
- PDF: https://itfrombit.biz/downloads/It-from-Bit-whitepaper.pdf

### Delivery pattern planning in retailing with transport and warehouse workload balancing (2022)

Mario Brcic et al. *Croatian Operational Research Review*, 2022.

Documents the methodology and results of the supply chain optimization engagement with Konzum (Croatia's largest retail chain) during the COVID-19 pandemic. Presents a discrete optimization model for weekly delivery pattern planning that balances warehouse and transportation utilization while maintaining service levels for fresh food across hundreds of stores in the CEE region.

- HRČAK: https://hrcak.srce.hr/280266

## Founder's full publication record

For Mario Brcic's complete publication record, citation metrics, and pre-prints, see Google Scholar: https://scholar.google.com/citations?user=rTdMHv8AAAAJ