Yu Zhu (祝宇) Ph.D. Candidate, Information SystemsUniversity of Utah, USA
Ph.D., FinanceZhejiang University, China
Yu Zhu
published on 2023-06-19 What’s an Investor Network, how to build one, and what can we do with it?
One table to compare popular tokenization methods: BPE, WordPiece, and SentencePiece.
This article comapres the implementation details between the original Transformer and GPT. These tricks are critical to performance but not always explained in the paper.
In a setting of PEAD (post-earnings-announcement-drift) prediction using earnings call transcripts, I found Transformers (deep learning models) have a larger performance lead on extreme data points (data at the tails of the distribution).
A highly efficient (>10x speedup) and concise (core part is less than 40 lines) event study R program that replicates WRDS’s SAS version.
How date and time are stored/processed in R and SAS, and how to use them wisely in WRDS or in your daily programming.
Yu Zhu
published on 2023-05-26 As a Git non-prouser, I found these tips very helpful.
Yu Zhu
published on 2023-05-26 Some facts on earnings announcement and analyst revision that you may not know before.
Yu Zhu
published on 2023-05-26 How to choose the right expected return model?
Quick recipe for a synthetic control study
Quick recipe for a DD study
Under what conditions does a significant coefficient means causality?
Bypass WRDS’s DUO verification
Downloading with Rsync could be 10X to 100X faster than downloading from Web or PostgreSQL
Indexing a row from Pandas is order of magnitudes slower than indexing from a native dict
or numpy.array
10K/Q are only available to the public several days after the fiscal period end, how does WRDS Factors deal with that?
Yu Zhu
published on 2023-02-12 How to extract items from 10K/Q files
Find the millisecond-level earnings event time by combining Captial IQ and RavenPack
The issue and my conversation with WRDS
How to query the surrounding days given an event?