1. Utilized Scala and PySpark to generate the dataset and modified the ETL pipeline to integrate additional features.2. Proposed a model-based feature selection method, GateNet, to identify and select approximately 30 useful features for enhancing the ad conversion model.3. Applied Deep Cross Network (DCN) to effectively capture feature interactions, resulting in an increase of over 0.02 in GAUC and over 0.04 in AUC for the ad conversion model.

1. Mine alpha factors based on U.S stock market data using genetic programming. Optimize alpha performance with regularization techniques and insert random noises to add to robustness.2. Implement a stratified backtesting framework to test the performance of alpha factors on different groups of stocks.3. Read and do research on related papers on alpha mining. Summarize basic ideas and reproduce python codes accordingly.4. Contribute to open-source python libraries like gplearn and alphalens. Adapt and add functions to support more stable and advanced use.

1. Collect relevant publications information using RestAPI and web scraping.2. Perform data cleaning and store data using both RDBMS and MongoDB based on different needs on query efficiency and data scalability.3. Use python pandas and sklearn to analyze publications that involved self-plagiarism from different perspective like reasons and categories. Data visualization with seaborn and matplotlib.4. Cultivate project management skills. Design and schedule the project from the beginning. Automate codes for later use.

1. In-depth participation in data analysis projects with four client companies. Independent research on related projects, financial data and revenue situations. Communication with clients regarding the accuracy and scheme of the available data.2. Use data analysis tools like SQL and Python to clean and process massive amount of data.3. Utilize big data tools like Spark SQL and Hive to analyze data of millions of entries.

Course VE215 Circuit Analysis Teaching Assistant1. Conduct tutorials and review sessions to reinforce understanding of circuit analysis techniques.2. Assist students during laboratory sessions to ensure smooth execution of experiments.3. Offer regular office hours to address individual student concerns and provide additional assistance.

Lab of Data Communication and Engineering RA. Responsible of algorithm implementation with focus on time series analysis and user purchase desire prediction in a company-based project. Use methods like LSTM, ARIMA and RNN to compare proficiency and accuracy.

Lab of BASICS. Led by SJTU falculty Xiaoju Dong. Participated in projects that focused on data visualization and analysis. Use python, flask, javascript and D3 to design systems that visualize web assets. The project was finally awarded the nominee prize at ChinaVis competition.