I helped with writing part of the book The Internationalization of RMB: Institutional Evolution and Challenges under my mentor Prof. Benhua Wei (former Director-General in International Department, the People’s Bank of China and former Deputy Administrator of State Administration of Foreign Exchange (SAFE)).

It is my first time to be responsible for writing parts of a book. It is a challenging and useful experience for me, to better understand RMB internationalization and how to write a good book.

It is our solution of 2018 MCM contest, our result got Meritorious award (first prize). During the contest, I am responsible for constructing models and writing the paper.

It is a brief pipeline to extract data from datasets in here

In this work, I use R, Bash and Python to extract different countries different indicators in different years. The data have some property: big, not unified(.RData or .csv), some have mistakes. It is very sparse so it waste many storage. And the conversion of Rdata to csv leads some mistakes, so it needs very careful examination and check work. At first I want to store all of them in HDF5 for better IO, but people in my girl friend’s working team are’t familiar with codes, so I store them in csv. I also think about later work(for example, basic statistical work, model the interaction and time series, maybe a hierarchical time series machine learning model), but I am too busy to help my little bragger to do all kinds of things.

2019/6/18 毕业典礼，因为懒，图片都没有P就放上来了。

I tried to crawl company information from crunchbase and owler. The websites have some basic anti-crawling techniques. So I use chromewhip to cheat the website and crawl information successfully.

See codes here: https://github.com/mengmeng12/crawl_company_info/

This is the final project of Big Data course. You could find the source could here: https://github.com/mengmeng12/ml_strategy

My undergraduate thesis: Analysis of the characteristics of China’s national debt yield curve and macroeconomic variables

My first blog