地球资源数据云——数据资源详情

Amazon_Sales_Dataset

该数据集《Amazon_Sales_Dataset》主要用于回归/预测任务，数据形态以文本为主，应用场景偏向文本内容分析。 题目说明：Time - Series Sales Data for EDA, Visualization, and Machine Learning 任务类型：文本回归/预测。 建议流程：先做文本清洗与分词，再比较 TF - IDF+线性模型 与 预训练语言模型。 评估建议：使用分层切分或交叉验证，优先关注 F1、Recall、AUC 等分类指标。 可用文件：amazon_sales_dataset.csv。 <h2> About the Dataset</h2> <p> This dataset contains <b>Amazon - style e - commerce sales data</b> created for <b>data analysis, visualization, and machine learning</b>. It captures realistic <b>time - series sales patterns</b>, pricing, discounts, customer regions, and ratings across multiple product categories. </p> <h2> Dataset Highlights</h2> <ul> <li> Time - series order data</li> <li> Multiple product categories</li> <li> Price & discount analysis</li> <li> Regional customer behavior</li> <li>⭐ Ratings & review metrics</li> <li> Revenue calculations</li> </ul> <h2> Columns Included</h2> <p> order_id, order_date, product_id, product_category, price, discount_percent, discounted_price, quantity_sold, total_revenue, customer_region, payment_method, rating, review_count </p> <h2> Use Cases</h2> <ul> <li> Sales forecasting</li> <li> Exploratory Data Analysis (EDA)</li> <li> Discount & revenue impact analysis</li> <li> Regional demand trends</li> <li> Machine learning model training</li> </ul>