A cleaned, verified product catalog of 23,000+ items from Walmart and Target with preserved UPC barcodes, designed for data scientists and e-commerce developers. The dataset removes common issues like truncated barcodes and tracking tokens, offering institutional-grade data in multiple formats (CSV, JSONL, SQLite) with a free 100-row preview and full commercial license available.
This tutorial introduces a framework for classifying large language models used as variation operators in metaheuristics, organized around two descriptors: the type of prompt-conditioning information (Numeric, Symbolic, Linguistic) and artifact persistence (what survives the model call). It provides practitioners with tools to build, classify, and select LLM-based operators through templates, method surveys, and cost-aware decision guides.