文创产品市场分析数据

1.竞品与跨境布局：针对 TOP5 竞品占据 10% 市场份额的分散格局，通过分析用户聚类数据，最佳 k 值 = 2时，可锁定两类核心客群 —— 文化收藏爱好者（关注传统元素）和科技尝鲜者（重视 AR 技术体验），推出差异化产品组合。同时，根据跨境销售占比情况制定跨境营销策略，拓展海外市场。
2.供应商合作评估：可为文创产品的原材料供应商、生产设备供应商等外部合作伙伴提供决策支持，例如通过对高频生产模式（如非遗工坊手工+智能裁切）的深入分析，以及对文化元素偏好（如传统元素95%）的精准洞察，可以精准把握市场趋势，据此加大对该生产模式配套产品的研发和供应力度。1.数据采集：从芝麻信用平台获取杭州西创文化创意有限公司运营产生的基础数据，如企业实力标运营数据（全渠道GMV分布、溢价率波动、竞品市场占有率、跨境销售占比（%）等），整合企业自行产生的产品相关数据（产品分类、产品ID、IP开发模式、生产模式、技术应用层级、文化元素融合度等）等信息，对数据进行清洗及预处理：通过 3σ 原则识别溢价率波动、跨境销售占比等数值型数据，根据业务逻辑对异常值进行修正，如对溢价率>300%的记录，采用Winsorize缩尾处理（上下1%截断）；
2.数据结构中产品id为主键，用于区分不同数据
3.使用 K - Means 算法进行聚类分析，基于技术应用层级、文化元素融合度、生产模式这三个特征对产品分类进行优化，首先使用label_encoders对技术应用层级、文化元素融合度和生产模式进行编码操作，提取特征，通过计算不同簇数（k 值从 2 到 10）下的轮廓系数来寻找最佳的 k 值，最后使用最佳的 k 值进行 K - Means 聚类，并输出聚类类别；输出聚类类别为0与1，说明该文创产品市场基于这三个特征可以大致分为两个细分市场。聚类类别 0为传统工艺主导型文创产品，面向追求传统、工艺性强、文化元素原汁原味的消费者群体；聚类类别 1：科技融合创新型文创产品，更受追求创新技术应用、文化元素与现代科技融合的消费者青睐。

1. Competitor Analysis and Cross-border Layout: Facing the fragmented market pattern where the TOP5 competitors occupy 10% of the total market share, through analyzing user clustering data, when the optimal k value = 2, two core customer groups can be identified — cultural collection enthusiasts (who focus on traditional elements) and tech trailblazers (who value AR technology experience), to launch differentiated product portfolios. Meanwhile, formulate cross-border marketing strategies based on the cross-border sales share to expand overseas markets.
2. Supplier Cooperation Evaluation: Provide decision support for external partners such as raw material suppliers and production equipment suppliers of cultural and creative products. For example, through in-depth analysis of high-frequency production modes (such as intangible cultural heritage workshop handicraft + intelligent cutting) and accurate insights into cultural element preferences (e.g., 95% for traditional elements), the market trend can be accurately grasped, and accordingly increase the R&D and supply of products supporting this production mode.
1. Data Collection: Obtain basic data generated from the operation of Hangzhou Xichuang Cultural and Creative Co., Ltd. from the Sesame Credit platform, such as enterprise strength indicator operation data (omni-channel GMV distribution, premium rate fluctuation, competitor market share, cross-border sales share (%) etc.), and integrate product-related data generated by the enterprise itself (product category, product ID, IP development mode, production mode, technology application level, cultural element integration degree etc.). Clean and preprocess the data: identify numerical data such as premium rate fluctuation and cross-border sales share using the 3σ principle, and correct outliers based on business logic. For example, for records with a premium rate exceeding 300%, adopt Winsorize tailoring treatment (truncate the top and bottom 1%);
2. Data Structure: The product ID serves as the primary key to distinguish different data entries.
3. Clustering Analysis: Use the K-Means algorithm for clustering analysis to optimize product classification based on three features: technology application level, cultural element integration degree and production mode. First, use label_encoders to encode the three features to extract feature sets. Calculate the silhouette coefficient under different cluster numbers (k value ranges from 2 to 10) to find the optimal k value. Finally, perform K-Means clustering with the optimal k value and output the clustering categories; the output clustering categories are 0 and 1, indicating that the cultural and creative product market can be roughly divided into two market segments based on these three features. Clustering category 0 refers to traditional craft-dominated cultural and creative products, targeting consumer groups who pursue tradition, strong craftsmanship and authentic cultural elements; Clustering category 1 refers to technology-integrated innovative cultural and creative products, which are more favored by consumers who pursue innovative technology applications and the integration of cultural elements with modern technology.