使用 Selenium + BeautifulSoup 搭建可复用动态页爬虫，支持无限滚动与复杂 DOM；设计标准化 ETL 清洗/解析并写入 MySQL/PostgreSQL。
Built a reusable crawler for dynamic pages using Selenium + BeautifulSoup, supporting infinite scroll and complex DOM structures. Designed a standardized ETL pipeline.
基于 PostgreSQL 自动化采集与存储；特征工程与多模型预测（Random Forest、Gradient Boosting、ARIMA、Prophet）；输出 7 日预测与风险区间。
Automated data ingestion with PostgreSQL. Feature engineering + multi-model forecasting (Random Forest, Gradient Boosting, ARIMA, Prophet). Delivered 7-day forecasts and risk intervals.
搭建 KPI 体系（UV/PV、漏斗转化、留存、复购）；RFM + K-means 用户分群，识别高价值与流失风险用户。
Built KPI system (UV/PV, funnel conversion, retention, repurchase). Segmented users via RFM + K-means, identifying high-value and churn-risk groups.
整合多业务系统数据，构建选品指标框架（销量、销售额、增长率、转化率、退款率等）；输出每日运营简报。
Integrated multi-system data to build a product selection metrics framework. Delivered daily operations briefs for rapid decision-making.
基于 NASA 开放数据的交互式小行星撞击模拟与分析平台；负责 Prediction 模块，实现 API 接入与可视化联动。
Web-based interactive asteroid impact simulation platform using NASA open data. Led the Prediction module: API integration and visualization linkage.
基于问卷数据构建分析数据集；描述统计、分组比较与相关分析探索社交网络使用与结果的关系。
Built an analysis dataset from survey data. Used descriptive stats and correlation analysis to explore links between social network usage and outcomes.