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{187355,
        author = {DR MUTHUSENTHIL and S KRITTHIKA and G LOKESH and S LOKESHKUMAR},
        title = {LIST2CART - AI POWERED PERSONAL SHOPPING ASSISTANT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4296-4301},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187355},
        abstract = {Traditional online shopping often becomes inconvenient when users provide free-form or unclear shopping lists, leading to mismatched products, missing items, and time-consuming manual searches. To overcome these limitations, this paper presents List2Cart, an intelligent AI-based assistant that automatically interprets user-provided lists whether typed or spoken and converts them into an organized shopping cart on an e-commerce platform. The system uses an NLU-driven extraction pipeline to detect item names, quantities, preferred brands, and specific attributes from unstructured inputs. A semantic product-matching module then identifies suitable items in the catalog and prioritizes them using contextual rules, user preference cues, price considerations, and stock availability. When the input is ambiguous or has multiple valid interpretations, the system offers smart alternatives and clarifying suggestions.
List2Cart features dedicated interfaces for both shoppers and administrators, ensuring smooth product handling, cart review, and catalog updates. A lightweight recommendation layer further improves user experience by proposing complementary and commonly paired items. In its initial development, the platform relies on rule-based processing, similarity metrics, and deterministic ranking methods due to the absence of large volumes of training data. However, the architecture is designed to evolve toward advanced AI techniques including transformer-based NLU, collaborative filtering, and neural ranking models as richer datasets become available. Analytical tools are also integrated to study user patterns, refine product mapping, and enhance search accuracy over time. By providing a structured, AI-enhanced workflow for understanding user intent, retrieving relevant products, and assembling a complete cart, List2Cart significantly streamlines the shopping experience and brings a more intuitive, automated approach to e-commerce.},
        keywords = {Shopping List Interpretation, Product Retrieval, Cart Automation, Natural Language Processing, Recommendation Systems, E-commerce Intelligence.},
        month = {November},
        }