Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{209303,
        author = {Dr MK Jayanthi Kannan and Anshuman Sharma and Aditya and Anshu Kumar and Srijan Sahu and Nikhil Rajput and Ishaan Priyadarshini},
        title = {CarbonIQ: AI-Powered Intelligent Carbon Credit Marketplace and Constrained Portfolio Optimization Platform},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {0-0},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209303},
        abstract = {The rapid acceleration of corporate net-zero commitments has created unprecedented demand in the Voluntary Carbon Market (VCM). However, the existing carbon credit ecosystem suffers from pervasive systemic deficiencies, including severe information asymmetry, fragmented registry architectures (Verra VCS, Gold Standard, American Carbon Registry), opaque broker markup fees, and critical greenwashing vulnerabilities stemming from questionable project additionality and impermanence. To address these critical market bottlenecks, this research presents 'CarbonIQ', an intelligent, end-to-end AI-powered carbon credit marketplace and decision-support optimization platform. CarbonIQ introduces a rigorous 7-dimension objective quality evaluation framework evaluating additionality, permanence, MRV rigor, baseline robustness, co-benefits, execution track record, and financial viability to eliminate subjective bias in project evaluation. The platform embodies an explainable multi-factor recommendation engine that mathematically aligns buyer-specified budget, vintage, and co-benefit preferences while surfacing transparent positive match reasons and negative trade-offs. Furthermore, CarbonIQ formulates and solves a constrained linear portfolio optimization model that allocates capital across diversified offset candidates to satisfy exact volume and budgetary targets while minimizing Herfindahl-Hirschman concentration risk. To ensure verifiable compliance, a Retrieval-Augmented Generation (RAG) auditing assistant is integrated, employing dense vector embeddings and pgvector semantic retrieval over complex Project Design Documents (PDDs) to provide transparent, paragraph-level evidentiary citations. The complete platform is engineered as a responsive, production-grade full-stack system utilizing Next.js 16, FastAPI, and PostgreSQL. Empirical validation confirms that CarbonIQ achieves sub-45ms optimization convergence, reduces portfolio concentration risk by 58%, and delivers 94.2% recommendation precision, establishing a new paradigm for integrity and auditability in environmental finance.},
        keywords = {Voluntary Carbon Markets, Artificial Intelligence, Portfolio Optimization, Explainable AI, Retrieval-Augmented Generation, Carbon Credits, Greenwashing Mitigation, ESG Decision-Support, Herfindahl Concentration Index.},
        month = {October},
        }