|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/generative-ai-for-retail-analysts/
课程评论：没有评论
课程名称：零售分析师的生成性人工智能 课程概述：该课程全面探讨了生成性人工智能如何通过智能自动化、增强个性化和实时决策支持来变革零售行业。参与者将先了解生成性人工智能背后的基础技术，包括大型语言模型（LLMs）、扩散模型和变压器架构。课程着重强调生成性人工智能在现代零售数据分析中的作用，特别是与传统预测人工智能方法的对比。学习者将掌握提示工程的艺术，包括制作有效提示的技巧、使用零样本、一样本和少样本学习，并为日常分析任务部署可重用的提示模板。 通过应用练习，参与者将利用生成性人工智能创建客户画像、分析购物篮和旅程数据，并实施针对性信息策略的客户流失预测。接着，课程转向商品和库存管理，应用生成性人工智能生成产品描述、识别替代模式及优化货架布局。它还涵盖了需求规划，包括缺货/过剩模拟、经济订货量（EOQ）和再订货点叙述以及使用天气和事件等外部信号进行的预测。 高级模块重点关注定价和促销策略，包括打折策略生成、动态定价模拟和促销投资回报分析。课程还整合了使用大型语言模型的情感分析、竞争对手定价智能和社交媒体趋势挖掘，以增强竞争优势。在操作层面，学习者将自动生成执行摘要、仪表盘图表，并使用自然语言查询业务数据。最后，课程探讨了部署人工智能驱动的店内助手、常见问题解答机器人和与客户关系管理系统（CRM）集成的POS聊天机器人，以提高店内效率。 来自亚马逊、塔吉特和丝芙兰的案例研究强调了实际应用，同时提供了超过1000个生成性人工智能提示的精选集合，使学习者能够在零售分析领域运用这些方法。
This course provides a comprehensive exploration of how Generative AI is transforming the retail industry through intelligent automation, enhanced personalization, and real-time decision support. Participants will begin by understanding the foundational technologies behind Generative AI, including Large Language Models (LLMs), Diffusion Models, and Transformer architectures. Emphasis is placed on the role of Generative AI in modern retail data analytics, especially in contrast to traditional predictive AI methods.Learners will master the art of prompt engineering, including crafting effective prompts, using zero-shot, one-shot, and few-shot learning, and deploying reusable prompt templates for daily analytics tasks. Through applied exercises, participants will use Generative AI to create customer personas, analyze basket and journey data, and implement churn prediction with tailored messaging strategies.The course then shifts to merchandising and inventory, where Generative AI is applied to generate product descriptions, identify substitution patterns, and optimize shelf layouts. It also covers demand planning through stockout/overstock simulations, EOQ and reorder point narratives, and forecasting with external signals such as weather and events.Advanced modules focus on pricing and promotions, including markdown strategy generation, dynamic pricing simulations, and campaign ROI analysis. Sentiment analysis using LLMs, competitor pricing intelligence, and social media trend mining are also integrated to enhance competitive positioning.Operationally, learners will auto-generate executive summaries, charts for dashboards, and query business data using natural language. Finally, the course explores the deployment of AI-powered store assistants, FAQ bots, and CRM-integrated POS chatbots to enhance in-store efficiency.Case studies from Amazon, Target, and Sephora highlight real-world applications, while a curated collection of 1000+ Generative AI prompts equips learners to apply these methods across the retail analytics spectrum.
